Deploy sync_pilot dashboard - 2026-06-16 14:13

sync_pilot/dashboard/data_loader.py

@@ -110,11 +110,11 @@ def _resolved_data_root() -> Path:
             # "Extension" tab. ``_audit_hf.jsonl`` is the Space-only edit
             # history; it must come down on boot so writebacks append rather
             # than overwrite prior Space-side edits (same story as median).
-            "sync_pilot/outputs/gt_expansion/median_adjacent/*.json",
-            "sync_pilot/gt_expansion/median_adjacent/groundtruth/*.json",
-            "sync_pilot/gt_expansion/median_adjacent/groundtruth/_audit_hf.jsonl",
-            "sync_pilot/gt_expansion/median_adjacent/manifest.jsonl",
-            "sync_pilot/gt_expansion/median_adjacent/_review.json",
+            "sync_pilot/outputs/gt_expansion/median_adjacent_combined_500/*.json",
+            "sync_pilot/gt_expansion/median_adjacent_combined_500/groundtruth/*.json",
+            "sync_pilot/gt_expansion/median_adjacent_combined_500/groundtruth/_audit_hf.jsonl",
+            "sync_pilot/gt_expansion/median_adjacent_combined_500/manifest.jsonl",
+            "sync_pilot/gt_expansion/median_adjacent_combined_500/_review.json",
         ],
     )
     # The downloaded snapshot mirrors the repo tree, so the project-equivalent
@@ -210,19 +210,34 @@ def _manifest_path() -> Path:
 # In local mode ``_resolved_data_root()`` == ``config.DATA_DIR``, so existing
 # local read/write behaviour is unchanged.
 def _expansion_outputs_dir() -> Path:
-    return _resolved_data_root() / "outputs" / "gt_expansion" / "median_adjacent"
+    return _resolved_data_root() / "outputs" / "gt_expansion" / "median_adjacent_combined_500"
 
 
 def _expansion_groundtruth_dir() -> Path:
-    return _resolved_data_root() / "gt_expansion" / "median_adjacent" / "groundtruth"
+    return (
+        _resolved_data_root()
+        / "gt_expansion"
+        / "median_adjacent_combined_500"
+        / "groundtruth"
+    )
 
 
 def _expansion_review_path() -> Path:
-    return _resolved_data_root() / "gt_expansion" / "median_adjacent" / "_review.json"
+    return (
+        _resolved_data_root()
+        / "gt_expansion"
+        / "median_adjacent_combined_500"
+        / "_review.json"
+    )
 
 
 def _expansion_manifest_path() -> Path:
-    return _resolved_data_root() / "gt_expansion" / "median_adjacent" / "manifest.jsonl"
+    return (
+        _resolved_data_root()
+        / "gt_expansion"
+        / "median_adjacent_combined_500"
+        / "manifest.jsonl"
+    )
 
 
 def _taxonomy_path() -> Path:
@@ -367,6 +382,55 @@ def load_expansion_groundtruth() -> dict[str, dict[str, Any]]:
     return out
 
 
+@st.cache_data(ttl=300, show_spinner=False)
+def load_expansion_triage() -> dict[str, dict[str, Any]]:
+    """Load the ``_triage.json`` review-priority ranking for the expansion set.
+
+    Produced by ``scripts/triage_disagreement.py`` — a per-track priority score
+    (model disagreement + uncertainty) used to order the GT-review queue so the
+    highest-information tracks surface first. Returns ``{track_id: {priority,
+    disagreement, uncertainty, reasons, ...}}``; ``{}`` when the sidecar is
+    absent (triage not yet run / not in the snapshot), so the page degrades to
+    plain alphabetical order. The ``_triage.json`` sidecar rides the same
+    ``outputs/.../*.json`` publish + snapshot globs as the TrackRecords.
+    """
+    path = _expansion_outputs_dir() / "_triage.json"
+    if not path.exists():
+        return {}
+    try:
+        data = json.loads(path.read_text())
+    except Exception as e:  # noqa: BLE001
+        st.warning(f"Could not parse _triage.json: {e}")
+        return {}
+    out: dict[str, dict[str, Any]] = {}
+    for row in data.get("ranked", []):
+        tid = row.get("track_id")
+        if tid:
+            out[tid] = row
+    return out
+
+
+@st.cache_data(ttl=300, show_spinner=False)
+def load_cohorts() -> dict[str, str]:
+    """Load the ``gt_ingest/cohorts.json`` track→cohort map.
+
+    Cohorts: ``catalog`` (Median eval set), ``ext`` (prior expansion), and
+    ``ext-median`` (the Spotify-sourced Median playlist tracks, pooled into the
+    combined_500 expansion but tagged distinctly for focused annotation). Built
+    by ``scripts/build_cohorts.py``. Returns ``{track_id: cohort}``; ``{}`` when
+    absent so the GT-review page degrades to its undivided Extension view.
+    """
+    path = _resolved_data_root() / "gt_ingest" / "cohorts.json"
+    if not path.exists():
+        return {}
+    try:
+        data = json.loads(path.read_text())
+    except Exception as e:  # noqa: BLE001
+        st.warning(f"Could not parse cohorts.json: {e}")
+        return {}
+    return data.get("cohorts", {})
+
+
 @st.cache_data(ttl=600, show_spinner=False)
 def load_subtypes_by_family() -> dict[str, list[str]]:
     """Parse dim 2 (genre subtype) from ``taxonomy.md`` grouped by parent
@@ -667,8 +731,8 @@ def save_expansion_gt_edit(
     tmp.replace(gt_path)
 
     if in_hf:
-        rel = f"sync_pilot/gt_expansion/median_adjacent/groundtruth/{track_id}.json"
-        rel_audit = f"sync_pilot/gt_expansion/median_adjacent/groundtruth/{audit_name}"
+        rel = f"sync_pilot/gt_expansion/median_adjacent_combined_500/groundtruth/{track_id}.json"
+        rel_audit = f"sync_pilot/gt_expansion/median_adjacent_combined_500/groundtruth/{audit_name}"
         _hf_writeback(
             [(gt_path, rel), (audit_path, rel_audit)],
             commit_message=f"gt-review ext: {track_id}.{field}",
@@ -725,8 +789,8 @@ def save_expansion_description(
     tmp.replace(track_path)
 
     if in_hf:
-        rel = f"sync_pilot/outputs/gt_expansion/median_adjacent/{track_id}.json"
-        rel_audit = f"sync_pilot/gt_expansion/median_adjacent/groundtruth/{audit_name}"
+        rel = f"sync_pilot/outputs/gt_expansion/median_adjacent_combined_500/{track_id}.json"
+        rel_audit = f"sync_pilot/gt_expansion/median_adjacent_combined_500/groundtruth/{audit_name}"
         _hf_writeback(
             [(track_path, rel), (audit_path, rel_audit)],
             commit_message=f"gt-review ext desc: {track_id}",
@@ -818,7 +882,7 @@ def save_expansion_review(state: dict[str, dict[str, Any]]) -> None:
 
     if in_hf:
         _hf_writeback(
-            [(p, "sync_pilot/gt_expansion/median_adjacent/_review.json")],
+            [(p, "sync_pilot/gt_expansion/median_adjacent_combined_500/_review.json")],
             commit_message="gt-review ext: update _review.json",
         )
     load_expansion_review.clear()

sync_pilot/dashboard/views/gt_review.py

@@ -43,10 +43,12 @@ from sync_pilot.dashboard.data_loader import (
     _data_source,
     _expansion_groundtruth_dir,
     _groundtruth_dir,
+    load_cohorts,
     load_expansion_groundtruth,
     load_expansion_manifest,
     load_expansion_review,
     load_expansion_tracks,
+    load_expansion_triage,
     load_groundtruth,
     load_manifest,
     load_review,
@@ -379,6 +381,14 @@ def _reviewed_track_ids(
     return out
 
 
+def _triage_why(entry: dict[str, Any] | None) -> str:
+    """Compact one-line 'why this ranks high' from a triage entry's reasons."""
+    if not entry:
+        return ""
+    reasons = entry.get("reasons") or []
+    return "; ".join(str(r) for r in reasons[:2])
+
+
 def _build_dataframe(
     tracks: list[dict[str, Any]],
     gt_by_id: dict[str, dict[str, Any]],
@@ -386,29 +396,40 @@ def _build_dataframe(
     reviewed: set[str],
     *,
     dataset: str,
+    triage: dict[str, dict[str, Any]] | None = None,
 ) -> pd.DataFrame:
     """Assemble the slim per-track row list for the overview table.
 
     Column ordering here drives the visual ordering. The editor panel
     handles all per-category details — the table is now strictly an
     navigation/triage surface: identity + Genre (GT) for at-a-glance
-    grouping + Reviewed checkmark.
+    grouping + Reviewed checkmark + review-priority columns.
+
+    ``triage`` (from ``load_expansion_triage``) supplies the per-track
+    disagreement/uncertainty priority that drives the default sort. When a
+    track has no triage entry (e.g. the catalog set, which has no
+    ``_triage.json``), priority falls back to 0.0 / empty so the columns
+    stay present and the concat across datasets keeps a uniform schema.
     """
+    triage = triage or {}
     rows: list[dict[str, Any]] = []
     for tr in tracks:
         tid = tr["track_id"]
         gt = gt_by_id.get(tid)
         meta = tr.get("metadata") or {}
         m = manifest.get(tid) or {}
+        t_entry = triage.get(tid)
         rows.append(
             {
                 "dataset": dataset,
                 "track_id": tid,
+                "priority": round(float((t_entry or {}).get("priority") or 0.0), 3),
                 "title": meta.get("title_tr") or tid,
                 "artist": (gt or {}).get("artist") or "",
                 "year": (gt or {}).get("year"),
                 "youtube": m.get("youtube_url") or meta.get("youtube_url") or "",
                 "genre_family": (gt or {}).get("genre_family") or "",
+                "why": _triage_why(t_entry),
                 "reviewed": tid in reviewed,
             }
         )
@@ -609,6 +630,22 @@ def _column_config() -> dict[str, Any]:
         "track_id": st.column_config.TextColumn(
             "Track ID", width="small", disabled=True
         ),
+        "priority": st.column_config.NumberColumn(
+            "Priority",
+            width="small",
+            disabled=True,
+            format="%.3f",
+            help=(
+                "Review priority from scripts/triage_disagreement.py: model "
+                "disagreement (audio-vs-lyric mood, classifier-vs-LLM theme) + "
+                "uncertainty. Higher = more information gained by reviewing it. "
+                "0.000 means no triage data (e.g. catalog set)."
+            ),
+        ),
+        "why": st.column_config.TextColumn(
+            "Why", width="large", disabled=True,
+            help="Top conflict/uncertainty reasons behind the priority score.",
+        ),
         "title": st.column_config.TextColumn(
             "Title", width="medium", disabled=True
         ),
@@ -1124,6 +1161,18 @@ def render() -> None:
     ext_tracks = load_expansion_tracks()
     ext_gt_by_id = load_expansion_groundtruth()
     ext_manifest = load_expansion_manifest()
+    ext_triage = load_expansion_triage()
+    cohorts = load_cohorts()
+    # The combined_500 expansion pool holds two cohorts: the prior expansion
+    # ("ext") and the Spotify-sourced Median playlist tracks ("ext-median").
+    # Split them so each gets its own review tab; ext-median tracks carry the
+    # same prior INFER/predicted tags every other extension track does.
+    ext_median_tracks = [
+        t for t in ext_tracks if cohorts.get(t.get("track_id")) == "ext-median"
+    ]
+    ext_only_tracks = [
+        t for t in ext_tracks if cohorts.get(t.get("track_id")) != "ext-median"
+    ]
     review = load_review()
     ext_review = load_expansion_review()
     taxonomy = load_taxonomy()
@@ -1149,14 +1198,19 @@ def render() -> None:
     n_tracks_reviewed, n_curated_tags = _verification_summary(review)
     n_ext_reviewed, n_ext_curated_tags = _verification_summary(ext_review)
     n_total_tracks = len(tracks)
-    n_ext_tracks = len(ext_tracks)
+    n_ext_tracks = len(ext_only_tracks)
+    n_ext_median_tracks = len(ext_median_tracks)
     n_categories = len(CATEGORIES)
     coverage_pct = (
         (n_tracks_reviewed / n_total_tracks * 100) if n_total_tracks else 0.0
     )
+    _ext_median_caption = (
+        f" Ext-Median: **{n_ext_median_tracks}** tracks."
+        if n_ext_median_tracks else ""
+    )
     st.caption(
         f"Catalog: **{n_total_tracks}** tracks, **{n_categories}** categories "
-        f"per track. Extension: **{n_ext_tracks}** tracks. "
+        f"per track. Extension: **{n_ext_tracks}** tracks.{_ext_median_caption} "
         f"Reviewed so far: **{n_tracks_reviewed}** catalog tracks "
         f"({coverage_pct:.1f}% catalog coverage; {n_curated_tags} total "
         f"curated INFER tags), plus **{n_ext_reviewed}** extension tracks "
@@ -1166,14 +1220,33 @@ def render() -> None:
     reviewed = _reviewed_track_ids(review, _groundtruth_dir())
     ext_reviewed = _reviewed_track_ids(ext_review, _expansion_groundtruth_dir())
 
-    dataset_filter = st.radio(
-        "Dataset filter",
-        options=["All", "Catalog", "Extension"],
-        index=0,
-        horizontal=True,
-        key="gt_review_dataset_filter",
-        label_visibility="collapsed",
-    )
+    filt_col, sort_col = st.columns([3, 2])
+    with filt_col:
+        _filter_options = ["All", "Catalog", "Extension"]
+        if ext_median_tracks:
+            _filter_options.append("Ext-Median")
+        dataset_filter = st.radio(
+            "Dataset filter",
+            options=_filter_options,
+            index=0,
+            horizontal=True,
+            key="gt_review_dataset_filter",
+            label_visibility="collapsed",
+        )
+    with sort_col:
+        # Default ON: surface the highest-disagreement tracks first so the
+        # review sprint spends effort where a label is most informative.
+        prioritize = st.toggle(
+            "Sort by review priority (disagreement)",
+            value=bool(ext_triage),
+            key="gt_review_prioritize",
+            help=(
+                "Order the queue by the triage score (audio-vs-lyric mood + "
+                "classifier-vs-LLM theme conflict + uncertainty). Off = "
+                "alphabetical. Requires _triage.json for the extension set."
+            ),
+            disabled=not ext_triage,
+        )
     frames = []
     if dataset_filter in ("All", "Catalog"):
         frames.append(
@@ -1181,10 +1254,27 @@ def render() -> None:
         )
     if dataset_filter in ("All", "Extension"):
         frames.append(
-            _build_dataframe(ext_tracks, ext_gt_by_id, ext_manifest, ext_reviewed, dataset="ext")
+            _build_dataframe(
+                ext_only_tracks, ext_gt_by_id, ext_manifest, ext_reviewed,
+                dataset="ext", triage=ext_triage,
+            )
+        )
+    if dataset_filter in ("All", "Ext-Median"):
+        # ext-median pools into the same combined_500 GT, so it reuses the
+        # expansion GT/manifest/review stores and save routing (dataset="ext").
+        frames.append(
+            _build_dataframe(
+                ext_median_tracks, ext_gt_by_id, ext_manifest, ext_reviewed,
+                dataset="ext", triage=ext_triage,
+            )
         )
     frames = [frame for frame in frames if not frame.empty]
     df = pd.concat(frames, ignore_index=True) if frames else pd.DataFrame()
+    if prioritize and not df.empty and "priority" in df.columns:
+        # Stable sort: priority desc, then keep alphabetical within ties.
+        df = df.sort_values(
+            by=["priority", "track_id"], ascending=[False, True]
+        ).reset_index(drop=True)
     column_config = _column_config()
 
     row_height_px = 35

sync_pilot/taxonomy/crosswalks.json

@@ -2,91 +2,981 @@
   "version": "0.1",
   "notes": "Canonical taxonomy IDs and aliases for inference labels. This file does not change taxonomy.md; it maps pipeline labels onto the draft taxonomy and sync-search language.",
   "terms": [
-    {"id": "genre.family.arabesk", "category": "genre", "dimension": "genre_family", "taxonomy_label": "arabesk", "display_label": "arabesk", "aliases": ["arabesk"]},
-    {"id": "genre.family.halk", "category": "genre", "dimension": "genre_family", "taxonomy_label": "halk", "display_label": "halk", "aliases": ["halk"]},
-    {"id": "genre.subtype.turku", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.türkü", "display_label": "türkü", "aliases": ["türkü", "turku"]},
-    {"id": "genre.subtype.uzun_hava", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.uzun-hava", "display_label": "uzun hava", "aliases": ["uzun hava", "uzun-hava"]},
-    {"id": "genre.subtype.roman_havasi", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.roman-havası", "display_label": "Roman havası", "aliases": ["Roman havası", "roman havası", "roman_havasi"], "requires_context": ["yore=roman or source-verified subtype before prose treats it as definitive"]},
-    {"id": "genre.family.rock", "category": "genre", "dimension": "genre_family", "taxonomy_label": "rock", "display_label": "rock", "aliases": ["rock"]},
-    {"id": "genre.subtype.anadolu_rock", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "rock.anadolu-rock-modern", "display_label": "Anadolu rock", "aliases": ["Anadolu rock", "anadolu rock"]},
-    {"id": "genre.subtype.anadolu_psych_rock", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "rock.anadolu-rock-psych-70s", "display_label": "Anadolu psych rock", "aliases": ["Anadolu psych rock", "anadolu psych rock"]},
-    {"id": "genre.family.sanat", "category": "genre", "dimension": "genre_family", "taxonomy_label": "sanat", "display_label": "sanat müziği", "aliases": ["sanat müziği", "sanat muzigi"]},
-    {"id": "genre.subtype.fasil", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "sanat.fasıl", "display_label": "fasıl", "aliases": ["fasıl", "fasil"]},
-    {"id": "genre.family.fantezi", "category": "genre", "dimension": "genre_family", "taxonomy_label": "fantezi", "display_label": "fantezi", "aliases": ["fantezi"]},
-    {"id": "genre.family.pop", "category": "genre", "dimension": "genre_family", "taxonomy_label": "pop", "display_label": "pop", "aliases": ["pop ballad", "dance pop"]},
-    {"id": "genre.subtype.acili_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.acılı-arabesk", "display_label": "acılı arabesk", "aliases": ["acılı arabesk", "acılı-arabesk", "acili arabesk"]},
-    {"id": "genre.subtype.fantezi_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.fantezi-arabesk", "display_label": "fantezi-arabesk", "aliases": ["fantezi-arabesk", "fantezi arabesk"], "requires_context": ["Murat decision pending: may move under fantezi family"]},
-    {"id": "genre.subtype.taverna_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.taverna-arabesk", "display_label": "taverna-arabesk", "aliases": ["taverna-arabesk", "taverna arabesk"]},
-    {"id": "genre.subtype.romantik_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.romantik-arabesk", "display_label": "romantik arabesk", "aliases": ["romantik arabesk", "romantik-arabesk"]},
-    {"id": "genre.subtype.kirik_hava", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.kırık-hava", "display_label": "kırık hava", "aliases": ["kırık hava", "kirik hava", "kırık-hava"]},
-    {"id": "genre.subtype.halay", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.halay", "display_label": "halay", "aliases": ["halay"]},
-    {"id": "genre.subtype.zeybek", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.zeybek", "display_label": "zeybek", "aliases": ["zeybek"]},
-    {"id": "genre.subtype.horon", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.horon", "display_label": "horon", "aliases": ["horon"]},
-    {"id": "genre.subtype.agit", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.ağıt", "display_label": "ağıt", "aliases": ["ağıt", "agit"]},
-    {"id": "genre.subtype.dini_halk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.dini-halk", "display_label": "dini halk", "aliases": ["dini halk", "dini-halk"]},
-    {"id": "genre.family.ozgun", "category": "genre", "dimension": "genre_family", "taxonomy_label": "özgün", "display_label": "özgün müzik", "aliases": ["özgün müzik", "ozgun muzik", "özgün"]},
-
-    {"id": "mood.aci", "category": "mood", "dimension": "mood", "taxonomy_label": "acı", "display_label": "acı", "aliases": ["acı", "aci"], "sync_search_terms": ["cathartic pain", "emotional intensity", "heartbreak drama"]},
-    {"id": "mood.huzun", "category": "mood", "dimension": "mood", "taxonomy_label": "hüzün", "display_label": "hüzün", "aliases": ["hüzün", "huzun"], "sync_search_terms": ["melancholy", "wistful sadness", "reflective longing"]},
-    {"id": "mood.ofke", "category": "mood", "dimension": "mood", "taxonomy_label": "öfke", "display_label": "öfke", "aliases": ["öfke", "ofke"], "sync_search_terms": ["anger", "defiance", "confrontation"]},
-    {"id": "mood.kabullenme", "category": "mood", "dimension": "mood", "taxonomy_label": "kabullenme", "display_label": "kabullenme", "aliases": ["kabullenme"], "sync_search_terms": ["resignation", "acceptance of fate", "weary resolve"]},
-    {"id": "mood.ironi", "category": "mood", "dimension": "mood", "taxonomy_label": "ironi", "display_label": "ironi", "aliases": ["ironi"], "sync_search_terms": ["irony", "sardonic", "bittersweet wit"]},
-    {"id": "mood.umut", "category": "mood", "dimension": "mood", "taxonomy_label": "umut", "display_label": "umut", "aliases": ["umut"], "sync_search_terms": ["hope", "optimism", "uplift"]},
-    {"id": "mood.ask", "category": "mood", "dimension": "mood", "taxonomy_label": "aşk", "display_label": "aşk", "aliases": ["aşk", "ask"], "sync_search_terms": ["romance", "devotion", "love"]},
-    {"id": "mood.heyecan", "category": "mood", "dimension": "mood", "taxonomy_label": "heyecan", "display_label": "heyecan", "aliases": ["heyecan"], "sync_search_terms": ["excitement", "momentum", "dance energy"]},
-    {"id": "mood.gurbet", "category": "mood", "dimension": "mood", "taxonomy_label": "gurbet", "display_label": "gurbet", "aliases": ["gurbet"], "sync_search_terms": ["exile longing", "diaspora", "homesickness"]},
-    {"id": "mood.nostaljik", "category": "mood", "dimension": "mood", "taxonomy_label": "nostaljik", "display_label": "nostaljik", "aliases": ["nostaljik"], "sync_search_terms": ["nostalgia", "memory", "looking back"]},
-
-    {"id": "instrument.baglama", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "bağlama", "display_label": "bağlama", "aliases": ["bağlama"]},
-    {"id": "instrument.ud", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "ud", "display_label": "ud", "aliases": ["ud"]},
-    {"id": "instrument.kanun", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kanun", "display_label": "kanun", "aliases": ["kanun"]},
-    {"id": "instrument.ney", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "ney", "display_label": "ney", "aliases": ["ney"]},
-    {"id": "instrument.darbuka", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "darbuka", "display_label": "darbuka", "aliases": ["darbuka"]},
-    {"id": "instrument.klarnet", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "klarnet", "display_label": "klarnet", "aliases": ["klarnet"]},
-    {"id": "instrument.electric_guitar", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "electric-guitar", "display_label": "electric guitar", "aliases": ["electric_guitar", "electric guitar"]},
-    {"id": "instrument.string_section", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "string-section", "display_label": "strings", "aliases": ["strings", "string-section"]},
-    {"id": "instrument.accordion", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "accordion", "display_label": "accordion", "aliases": ["accordion", "garmon"]},
-    {"id": "instrument.piano", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "piano", "display_label": "piano", "aliases": ["piano"]},
-    {"id": "instrument.cura", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "cura-bağlama", "display_label": "cura", "aliases": ["cura"]},
-    {"id": "instrument.electric_baglama", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "electric-bağlama", "display_label": "electric bağlama", "aliases": ["electric_baglama", "electric baglama", "electric bağlama"]},
-    {"id": "instrument.kemence_karadeniz", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "karadeniz-kemençesi", "display_label": "Karadeniz kemençesi", "aliases": ["kemence_karadeniz", "karadeniz kemençesi"]},
-    {"id": "instrument.kemence_klasik", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "klasik-kemençe", "display_label": "klasik kemençe", "aliases": ["kemence_klasik", "klasik kemençe"]},
-    {"id": "instrument.keman", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "keman", "display_label": "keman", "aliases": ["keman"]},
-    {"id": "instrument.mey", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "mey", "display_label": "mey", "aliases": ["mey"]},
-    {"id": "instrument.zurna", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "zurna", "display_label": "zurna", "aliases": ["zurna"]},
-    {"id": "instrument.kaval", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kaval", "display_label": "kaval", "aliases": ["kaval"]},
-    {"id": "instrument.def", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "def", "display_label": "def", "aliases": ["def"]},
-    {"id": "instrument.davul", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "davul", "display_label": "davul", "aliases": ["davul"]},
-    {"id": "instrument.kudum", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kudüm", "display_label": "kudüm", "aliases": ["kudum", "kudüm"]},
-    {"id": "instrument.choir", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "choir", "display_label": "choir", "aliases": ["choir"]},
-    {"id": "instrument.backing_vocals", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "backing-vocals", "display_label": "backing vocals", "aliases": ["backing_vocals", "backing vocals"]},
-
-    {"id": "vocal.config.male", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "solo-male", "display_label": "male vocals", "aliases": ["male_vocals", "solo-male"]},
-    {"id": "vocal.config.female", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "solo-female", "display_label": "female vocals", "aliases": ["female_vocals", "solo-female"]},
-    {"id": "vocal.config.duet", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "duet-mf", "display_label": "duet", "aliases": ["duet", "duet-mf"]},
-    {"id": "vocal.config.instrumental", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "instrumental", "display_label": "instrumental", "aliases": ["instrumental"]},
-    {"id": "vocal.technique.hancere", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "hançere", "display_label": "hançere", "aliases": ["hancere", "hançere"]},
-    {"id": "vocal.technique.gazel", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "gazel", "display_label": "gazel", "aliases": ["gazel"]},
-    {"id": "vocal.technique.duz_okuyus", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "düz-okuyuş", "display_label": "düz okuyuş", "aliases": ["duz_okuyus", "düz-okuyuş", "düz okuyuş"]},
-    {"id": "vocal.technique.taverna", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "taverna-style", "display_label": "taverna vocal", "aliases": ["taverna_vocal", "taverna-style"]},
-    {"id": "vocal.technique.call_response", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "call-and-response", "display_label": "call-and-response", "aliases": ["call-and-response", "call_response"]},
-    {"id": "vocal.technique.belt", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "bağırma", "display_label": "belt", "aliases": ["belt", "bağırma"]}
+    {
+      "id": "genre.family.arabesk",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "arabesk",
+      "display_label": "arabesk",
+      "aliases": [
+        "arabesk"
+      ]
+    },
+    {
+      "id": "genre.family.halk",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "halk",
+      "display_label": "halk",
+      "aliases": [
+        "halk"
+      ]
+    },
+    {
+      "id": "genre.subtype.turku",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.türkü",
+      "display_label": "türkü",
+      "aliases": [
+        "türkü",
+        "turku"
+      ]
+    },
+    {
+      "id": "genre.subtype.uzun_hava",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.uzun-hava",
+      "display_label": "uzun hava",
+      "aliases": [
+        "uzun hava",
+        "uzun-hava"
+      ]
+    },
+    {
+      "id": "genre.subtype.roman_havasi",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.oyun-havası.roman-havası",
+      "display_label": "Roman havası",
+      "aliases": [
+        "Roman havası",
+        "roman havası",
+        "roman_havasi"
+      ],
+      "requires_context": [
+        "yore=roman or source-verified subtype before prose treats it as definitive"
+      ]
+    },
+    {
+      "id": "genre.family.rock",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "rock",
+      "display_label": "rock",
+      "aliases": [
+        "rock"
+      ]
+    },
+    {
+      "id": "genre.subtype.anadolu_rock",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "rock.anadolu-rock-modern",
+      "display_label": "Anadolu rock",
+      "aliases": [
+        "Anadolu rock",
+        "anadolu rock"
+      ]
+    },
+    {
+      "id": "genre.subtype.anadolu_psych_rock",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "rock.anadolu-rock-psych-70s",
+      "display_label": "Anadolu psych rock",
+      "aliases": [
+        "Anadolu psych rock",
+        "anadolu psych rock"
+      ]
+    },
+    {
+      "id": "genre.family.sanat",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "sanat",
+      "display_label": "sanat müziği",
+      "aliases": [
+        "sanat müziği",
+        "sanat muzigi"
+      ]
+    },
+    {
+      "id": "genre.subtype.fasil",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "sanat.fasıl",
+      "display_label": "fasıl",
+      "aliases": [
+        "fasıl",
+        "fasil"
+      ]
+    },
+    {
+      "id": "genre.family.fantezi",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "fantezi",
+      "display_label": "fantezi",
+      "aliases": [
+        "fantezi"
+      ]
+    },
+    {
+      "id": "genre.family.pop",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "pop",
+      "display_label": "pop",
+      "aliases": [
+        "pop ballad",
+        "dance pop"
+      ]
+    },
+    {
+      "id": "genre.subtype.acili_arabesk",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "arabesk.acılı-arabesk",
+      "display_label": "acılı arabesk",
+      "aliases": [
+        "acılı arabesk",
+        "acılı-arabesk",
+        "acili arabesk"
+      ]
+    },
+    {
+      "id": "genre.subtype.fantezi_arabesk",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "arabesk.fantezi-arabesk",
+      "display_label": "fantezi-arabesk",
+      "aliases": [
+        "fantezi-arabesk",
+        "fantezi arabesk"
+      ],
+      "requires_context": [
+        "Murat decision pending: may move under fantezi family"
+      ]
+    },
+    {
+      "id": "genre.subtype.taverna_arabesk",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "arabesk.taverna-arabesk",
+      "display_label": "taverna-arabesk",
+      "aliases": [
+        "taverna-arabesk",
+        "taverna arabesk"
+      ]
+    },
+    {
+      "id": "genre.subtype.romantik_arabesk",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "arabesk.romantik-arabesk",
+      "display_label": "romantik arabesk",
+      "aliases": [
+        "romantik arabesk",
+        "romantik-arabesk"
+      ]
+    },
+    {
+      "id": "genre.subtype.kirik_hava",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.kırık-hava",
+      "display_label": "kırık hava",
+      "aliases": [
+        "kırık hava",
+        "kirik hava",
+        "kırık-hava"
+      ]
+    },
+    {
+      "id": "genre.subtype.halay",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.oyun-havası.halay",
+      "display_label": "halay",
+      "aliases": [
+        "halay"
+      ]
+    },
+    {
+      "id": "genre.subtype.zeybek",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.oyun-havası.zeybek",
+      "display_label": "zeybek",
+      "aliases": [
+        "zeybek"
+      ]
+    },
+    {
+      "id": "genre.subtype.horon",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.oyun-havası.horon",
+      "display_label": "horon",
+      "aliases": [
+        "horon"
+      ]
+    },
+    {
+      "id": "genre.subtype.agit",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.ağıt",
+      "display_label": "ağıt",
+      "aliases": [
+        "ağıt",
+        "agit"
+      ]
+    },
+    {
+      "id": "genre.subtype.dini_halk",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.dini-halk",
+      "display_label": "dini halk",
+      "aliases": [
+        "dini halk",
+        "dini-halk"
+      ]
+    },
+    {
+      "id": "genre.family.ozgun",
+      "category": "genre",
+      "dimension": "genre_family",
+      "taxonomy_label": "özgün",
+      "display_label": "özgün müzik",
+      "aliases": [
+        "özgün müzik",
+        "ozgun muzik",
+        "özgün"
+      ]
+    },
+    {
+      "id": "mood.aci",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "acı",
+      "display_label": "acı",
+      "aliases": [
+        "acı",
+        "aci"
+      ],
+      "sync_search_terms": [
+        "cathartic pain",
+        "emotional intensity",
+        "heartbreak drama"
+      ]
+    },
+    {
+      "id": "mood.huzun",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "hüzün",
+      "display_label": "hüzün",
+      "aliases": [
+        "hüzün",
+        "huzun"
+      ],
+      "sync_search_terms": [
+        "melancholy",
+        "wistful sadness",
+        "reflective longing"
+      ]
+    },
+    {
+      "id": "mood.ofke",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "öfke",
+      "display_label": "öfke",
+      "aliases": [
+        "öfke",
+        "ofke"
+      ],
+      "sync_search_terms": [
+        "anger",
+        "defiance",
+        "confrontation"
+      ]
+    },
+    {
+      "id": "mood.kabullenme",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "kabullenme",
+      "display_label": "kabullenme",
+      "aliases": [
+        "kabullenme"
+      ],
+      "sync_search_terms": [
+        "resignation",
+        "acceptance of fate",
+        "weary resolve"
+      ]
+    },
+    {
+      "id": "mood.ironi",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "ironi",
+      "display_label": "ironi",
+      "aliases": [
+        "ironi"
+      ],
+      "sync_search_terms": [
+        "irony",
+        "sardonic",
+        "bittersweet wit"
+      ]
+    },
+    {
+      "id": "mood.umut",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "umut",
+      "display_label": "umut",
+      "aliases": [
+        "umut"
+      ],
+      "sync_search_terms": [
+        "hope",
+        "optimism",
+        "uplift"
+      ]
+    },
+    {
+      "id": "mood.ask",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "aşk",
+      "display_label": "aşk",
+      "aliases": [
+        "aşk",
+        "ask"
+      ],
+      "sync_search_terms": [
+        "romance",
+        "devotion",
+        "love"
+      ]
+    },
+    {
+      "id": "mood.heyecan",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "heyecan",
+      "display_label": "heyecan",
+      "aliases": [
+        "heyecan"
+      ],
+      "sync_search_terms": [
+        "excitement",
+        "momentum",
+        "dance energy"
+      ]
+    },
+    {
+      "id": "mood.gurbet",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "gurbet",
+      "display_label": "gurbet",
+      "aliases": [
+        "gurbet"
+      ],
+      "sync_search_terms": [
+        "exile longing",
+        "diaspora",
+        "homesickness"
+      ]
+    },
+    {
+      "id": "mood.nostaljik",
+      "category": "mood",
+      "dimension": "mood",
+      "taxonomy_label": "nostaljik",
+      "display_label": "nostaljik",
+      "aliases": [
+        "nostaljik"
+      ],
+      "sync_search_terms": [
+        "nostalgia",
+        "memory",
+        "looking back"
+      ]
+    },
+    {
+      "id": "instrument.baglama",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "bağlama",
+      "display_label": "bağlama",
+      "aliases": [
+        "bağlama"
+      ]
+    },
+    {
+      "id": "instrument.ud",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "ud",
+      "display_label": "ud",
+      "aliases": [
+        "ud"
+      ]
+    },
+    {
+      "id": "instrument.kanun",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "kanun",
+      "display_label": "kanun",
+      "aliases": [
+        "kanun"
+      ]
+    },
+    {
+      "id": "instrument.ney",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "ney",
+      "display_label": "ney",
+      "aliases": [
+        "ney"
+      ]
+    },
+    {
+      "id": "instrument.darbuka",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "darbuka",
+      "display_label": "darbuka",
+      "aliases": [
+        "darbuka"
+      ]
+    },
+    {
+      "id": "instrument.klarnet",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "klarnet",
+      "display_label": "klarnet",
+      "aliases": [
+        "klarnet"
+      ]
+    },
+    {
+      "id": "instrument.electric_guitar",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "electric-guitar",
+      "display_label": "electric guitar",
+      "aliases": [
+        "electric_guitar",
+        "electric guitar"
+      ]
+    },
+    {
+      "id": "instrument.string_section",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "string-section",
+      "display_label": "strings",
+      "aliases": [
+        "strings",
+        "string-section"
+      ]
+    },
+    {
+      "id": "instrument.accordion",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "accordion",
+      "display_label": "accordion",
+      "aliases": [
+        "accordion",
+        "garmon"
+      ]
+    },
+    {
+      "id": "instrument.piano",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "piano",
+      "display_label": "piano",
+      "aliases": [
+        "piano"
+      ]
+    },
+    {
+      "id": "instrument.cura",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "cura-bağlama",
+      "display_label": "cura",
+      "aliases": [
+        "cura"
+      ]
+    },
+    {
+      "id": "instrument.electric_baglama",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "electric-bağlama",
+      "display_label": "electric bağlama",
+      "aliases": [
+        "electric_baglama",
+        "electric baglama",
+        "electric bağlama"
+      ]
+    },
+    {
+      "id": "instrument.kemence_karadeniz",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "karadeniz-kemençesi",
+      "display_label": "Karadeniz kemençesi",
+      "aliases": [
+        "kemence_karadeniz",
+        "karadeniz kemençesi"
+      ]
+    },
+    {
+      "id": "instrument.kemence_klasik",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "klasik-kemençe",
+      "display_label": "klasik kemençe",
+      "aliases": [
+        "kemence_klasik",
+        "klasik kemençe"
+      ]
+    },
+    {
+      "id": "instrument.keman",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "keman",
+      "display_label": "keman",
+      "aliases": [
+        "keman"
+      ]
+    },
+    {
+      "id": "instrument.mey",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "mey",
+      "display_label": "mey",
+      "aliases": [
+        "mey"
+      ]
+    },
+    {
+      "id": "instrument.zurna",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "zurna",
+      "display_label": "zurna",
+      "aliases": [
+        "zurna"
+      ]
+    },
+    {
+      "id": "instrument.kaval",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "kaval",
+      "display_label": "kaval",
+      "aliases": [
+        "kaval"
+      ]
+    },
+    {
+      "id": "instrument.def",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "def",
+      "display_label": "def",
+      "aliases": [
+        "def"
+      ]
+    },
+    {
+      "id": "instrument.davul",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "davul",
+      "display_label": "davul",
+      "aliases": [
+        "davul"
+      ]
+    },
+    {
+      "id": "instrument.kudum",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "kudüm",
+      "display_label": "kudüm",
+      "aliases": [
+        "kudum",
+        "kudüm"
+      ]
+    },
+    {
+      "id": "instrument.choir",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "choir",
+      "display_label": "choir",
+      "aliases": [
+        "choir"
+      ]
+    },
+    {
+      "id": "instrument.backing_vocals",
+      "category": "instrument",
+      "dimension": "instrumentation",
+      "taxonomy_label": "backing-vocals",
+      "display_label": "backing vocals",
+      "aliases": [
+        "backing_vocals",
+        "backing vocals"
+      ]
+    },
+    {
+      "id": "vocal.config.male",
+      "category": "vocal",
+      "dimension": "vocal_configuration",
+      "taxonomy_label": "solo-male",
+      "display_label": "male vocals",
+      "aliases": [
+        "male_vocals",
+        "solo-male"
+      ]
+    },
+    {
+      "id": "vocal.config.female",
+      "category": "vocal",
+      "dimension": "vocal_configuration",
+      "taxonomy_label": "solo-female",
+      "display_label": "female vocals",
+      "aliases": [
+        "female_vocals",
+        "solo-female"
+      ]
+    },
+    {
+      "id": "vocal.config.duet",
+      "category": "vocal",
+      "dimension": "vocal_configuration",
+      "taxonomy_label": "duet-mf",
+      "display_label": "duet",
+      "aliases": [
+        "duet",
+        "duet-mf"
+      ]
+    },
+    {
+      "id": "vocal.config.instrumental",
+      "category": "vocal",
+      "dimension": "vocal_configuration",
+      "taxonomy_label": "instrumental",
+      "display_label": "instrumental",
+      "aliases": [
+        "instrumental"
+      ]
+    },
+    {
+      "id": "vocal.technique.hancere",
+      "category": "vocal",
+      "dimension": "vocal_technique",
+      "taxonomy_label": "hançere",
+      "display_label": "hançere",
+      "aliases": [
+        "hancere",
+        "hançere"
+      ]
+    },
+    {
+      "id": "vocal.technique.gazel",
+      "category": "vocal",
+      "dimension": "vocal_technique",
+      "taxonomy_label": "gazel",
+      "display_label": "gazel",
+      "aliases": [
+        "gazel"
+      ]
+    },
+    {
+      "id": "vocal.technique.duz_okuyus",
+      "category": "vocal",
+      "dimension": "vocal_technique",
+      "taxonomy_label": "düz-okuyuş",
+      "display_label": "düz okuyuş",
+      "aliases": [
+        "duz_okuyus",
+        "düz-okuyuş",
+        "düz okuyuş"
+      ]
+    },
+    {
+      "id": "vocal.technique.taverna",
+      "category": "vocal",
+      "dimension": "vocal_technique",
+      "taxonomy_label": "taverna-style",
+      "display_label": "taverna vocal",
+      "aliases": [
+        "taverna_vocal",
+        "taverna-style"
+      ]
+    },
+    {
+      "id": "vocal.technique.call_response",
+      "category": "vocal",
+      "dimension": "vocal_configuration",
+      "taxonomy_label": "call-and-response",
+      "display_label": "call-and-response",
+      "aliases": [
+        "call-and-response",
+        "call_response"
+      ]
+    },
+    {
+      "id": "vocal.technique.belt",
+      "category": "vocal",
+      "dimension": "vocal_technique",
+      "taxonomy_label": "bağırma",
+      "display_label": "belt",
+      "aliases": [
+        "belt",
+        "bağırma"
+      ]
+    },
+    {
+      "id": "genre.arabesk-arabesk-pop",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "arabesk.arabesk-pop",
+      "display_label": "arabesk.arabesk-pop",
+      "aliases": [
+        "arabesk.arabesk-pop",
+        "arabesk-pop",
+        "arabesk pop"
+      ]
+    },
+    {
+      "id": "genre.halk-deyis",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.deyiş",
+      "display_label": "halk.deyiş",
+      "aliases": [
+        "halk.deyiş",
+        "deyiş",
+        "halk deyiş"
+      ]
+    },
+    {
+      "id": "genre.halk-oyun-havasi",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "halk.oyun-havası",
+      "display_label": "halk.oyun-havası",
+      "aliases": [
+        "halk.oyun-havası",
+        "oyun-havası",
+        "oyun havası"
+      ]
+    },
+    {
+      "id": "genre.pop-70s",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.70s",
+      "display_label": "pop.70s",
+      "aliases": [
+        "pop.70s",
+        "pop 70s",
+        "pop-70s"
+      ]
+    },
+    {
+      "id": "genre.pop-90s",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.90s",
+      "display_label": "pop.90s",
+      "aliases": [
+        "pop.90s",
+        "pop 90s",
+        "pop-90s"
+      ]
+    },
+    {
+      "id": "genre.pop-90s-pop",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.90s-pop",
+      "display_label": "pop.90s-pop",
+      "aliases": [
+        "pop.90s-pop",
+        "pop 90s pop"
+      ]
+    },
+    {
+      "id": "genre.pop-2000s-pop",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.2000s-pop",
+      "display_label": "pop.2000s-pop",
+      "aliases": [
+        "pop.2000s-pop",
+        "pop 2000s pop",
+        "pop.2000s"
+      ]
+    },
+    {
+      "id": "genre.pop-rock",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.rock",
+      "display_label": "pop.rock",
+      "aliases": [
+        "pop.rock",
+        "pop-rock",
+        "pop rock"
+      ]
+    },
+    {
+      "id": "genre.pop-ballad",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.ballad",
+      "display_label": "pop.ballad",
+      "aliases": [
+        "pop.ballad",
+        "pop-ballad",
+        "pop ballad"
+      ]
+    },
+    {
+      "id": "genre.pop-duygusal",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "pop.duygusal",
+      "display_label": "pop.duygusal",
+      "aliases": [
+        "pop.duygusal",
+        "duygusal",
+        "halk-pop"
+      ]
+    },
+    {
+      "id": "genre.rock-alternative",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "rock.alternative",
+      "display_label": "rock.alternative",
+      "aliases": [
+        "rock.alternative",
+        "alternative",
+        "alternatif"
+      ]
+    },
+    {
+      "id": "genre.rock-hard-rock",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "rock.hard-rock",
+      "display_label": "rock.hard-rock",
+      "aliases": [
+        "rock.hard-rock",
+        "hard-rock",
+        "hard rock"
+      ]
+    },
+    {
+      "id": "genre.sanat-tango",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "sanat.tango",
+      "display_label": "sanat.tango",
+      "aliases": [
+        "sanat.tango",
+        "tango"
+      ]
+    },
+    {
+      "id": "genre.ozgun-protest",
+      "category": "genre",
+      "dimension": "genre_subtype",
+      "taxonomy_label": "özgün.protest",
+      "display_label": "özgün.protest",
+      "aliases": [
+        "özgün.protest",
+        "protest"
+      ]
+    }
   ],
   "maest_hints": {
-    "Folk, World, & Country---Folk": ["genre.family.halk"],
-    "Folk, World, & Country---Laïkó": ["genre.family.fantezi", "genre.family.sanat"],
-    "Folk, World, & Country---Éntekhno": ["genre.family.ozgun", "genre.family.halk"],
-    "Folk, World, & Country---Hindustani": ["genre.family.halk"],
-    "Pop---Vocal": ["genre.family.pop", "genre.family.arabesk"],
-    "Pop---Ballad": ["genre.family.pop", "genre.family.fantezi"],
-    "Pop---Schlager": ["genre.family.fantezi", "genre.family.pop"],
-    "Pop---Chanson": ["genre.family.fantezi", "genre.family.pop"],
-    "Rock---Pop Rock": ["genre.family.rock"],
-    "Rock---Folk Rock": ["genre.subtype.anadolu_rock"],
-    "Rock---Prog Rock": ["genre.subtype.anadolu_psych_rock"],
-    "Rock---Psychedelic Rock": ["genre.subtype.anadolu_psych_rock"],
-    "Rock---Hard Rock": ["genre.family.rock"],
-    "Stage & Screen---Soundtrack": ["genre.family.pop"],
-    "Latin---MPB": ["genre.family.pop"]
+    "Folk, World, & Country---Folk": [
+      "genre.family.halk"
+    ],
+    "Folk, World, & Country---Laïkó": [
+      "genre.family.fantezi",
+      "genre.family.sanat"
+    ],
+    "Folk, World, & Country---Éntekhno": [
+      "genre.family.ozgun",
+      "genre.family.halk"
+    ],
+    "Folk, World, & Country---Hindustani": [
+      "genre.family.halk"
+    ],
+    "Pop---Vocal": [
+      "genre.family.pop",
+      "genre.family.arabesk"
+    ],
+    "Pop---Ballad": [
+      "genre.family.pop",
+      "genre.family.fantezi"
+    ],
+    "Pop---Schlager": [
+      "genre.family.fantezi",
+      "genre.family.pop"
+    ],
+    "Pop---Chanson": [
+      "genre.family.fantezi",
+      "genre.family.pop"
+    ],
+    "Rock---Pop Rock": [
+      "genre.family.rock"
+    ],
+    "Rock---Folk Rock": [
+      "genre.subtype.anadolu_rock"
+    ],
+    "Rock---Prog Rock": [
+      "genre.subtype.anadolu_psych_rock"
+    ],
+    "Rock---Psychedelic Rock": [
+      "genre.subtype.anadolu_psych_rock"
+    ],
+    "Rock---Hard Rock": [
+      "genre.family.rock"
+    ],
+    "Stage & Screen---Soundtrack": [
+      "genre.family.pop"
+    ],
+    "Latin---MPB": [
+      "genre.family.pop"
+    ]
   }
-}
+}

sync_pilot/taxonomy/crosswalks.json.bak

@@ -0,0 +1,92 @@
+{
+  "version": "0.1",
+  "notes": "Canonical taxonomy IDs and aliases for inference labels. This file does not change taxonomy.md; it maps pipeline labels onto the draft taxonomy and sync-search language.",
+  "terms": [
+    {"id": "genre.family.arabesk", "category": "genre", "dimension": "genre_family", "taxonomy_label": "arabesk", "display_label": "arabesk", "aliases": ["arabesk"]},
+    {"id": "genre.family.halk", "category": "genre", "dimension": "genre_family", "taxonomy_label": "halk", "display_label": "halk", "aliases": ["halk"]},
+    {"id": "genre.subtype.turku", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.türkü", "display_label": "türkü", "aliases": ["türkü", "turku"]},
+    {"id": "genre.subtype.uzun_hava", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.uzun-hava", "display_label": "uzun hava", "aliases": ["uzun hava", "uzun-hava"]},
+    {"id": "genre.subtype.roman_havasi", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.roman-havası", "display_label": "Roman havası", "aliases": ["Roman havası", "roman havası", "roman_havasi"], "requires_context": ["yore=roman or source-verified subtype before prose treats it as definitive"]},
+    {"id": "genre.family.rock", "category": "genre", "dimension": "genre_family", "taxonomy_label": "rock", "display_label": "rock", "aliases": ["rock"]},
+    {"id": "genre.subtype.anadolu_rock", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "rock.anadolu-rock-modern", "display_label": "Anadolu rock", "aliases": ["Anadolu rock", "anadolu rock"]},
+    {"id": "genre.subtype.anadolu_psych_rock", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "rock.anadolu-rock-psych-70s", "display_label": "Anadolu psych rock", "aliases": ["Anadolu psych rock", "anadolu psych rock"]},
+    {"id": "genre.family.sanat", "category": "genre", "dimension": "genre_family", "taxonomy_label": "sanat", "display_label": "sanat müziği", "aliases": ["sanat müziği", "sanat muzigi"]},
+    {"id": "genre.subtype.fasil", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "sanat.fasıl", "display_label": "fasıl", "aliases": ["fasıl", "fasil"]},
+    {"id": "genre.family.fantezi", "category": "genre", "dimension": "genre_family", "taxonomy_label": "fantezi", "display_label": "fantezi", "aliases": ["fantezi"]},
+    {"id": "genre.family.pop", "category": "genre", "dimension": "genre_family", "taxonomy_label": "pop", "display_label": "pop", "aliases": ["pop ballad", "dance pop"]},
+    {"id": "genre.subtype.acili_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.acılı-arabesk", "display_label": "acılı arabesk", "aliases": ["acılı arabesk", "acılı-arabesk", "acili arabesk"]},
+    {"id": "genre.subtype.fantezi_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.fantezi-arabesk", "display_label": "fantezi-arabesk", "aliases": ["fantezi-arabesk", "fantezi arabesk"], "requires_context": ["Murat decision pending: may move under fantezi family"]},
+    {"id": "genre.subtype.taverna_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.taverna-arabesk", "display_label": "taverna-arabesk", "aliases": ["taverna-arabesk", "taverna arabesk"]},
+    {"id": "genre.subtype.romantik_arabesk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "arabesk.romantik-arabesk", "display_label": "romantik arabesk", "aliases": ["romantik arabesk", "romantik-arabesk"]},
+    {"id": "genre.subtype.kirik_hava", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.kırık-hava", "display_label": "kırık hava", "aliases": ["kırık hava", "kirik hava", "kırık-hava"]},
+    {"id": "genre.subtype.halay", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.halay", "display_label": "halay", "aliases": ["halay"]},
+    {"id": "genre.subtype.zeybek", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.zeybek", "display_label": "zeybek", "aliases": ["zeybek"]},
+    {"id": "genre.subtype.horon", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.oyun-havası.horon", "display_label": "horon", "aliases": ["horon"]},
+    {"id": "genre.subtype.agit", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.ağıt", "display_label": "ağıt", "aliases": ["ağıt", "agit"]},
+    {"id": "genre.subtype.dini_halk", "category": "genre", "dimension": "genre_subtype", "taxonomy_label": "halk.dini-halk", "display_label": "dini halk", "aliases": ["dini halk", "dini-halk"]},
+    {"id": "genre.family.ozgun", "category": "genre", "dimension": "genre_family", "taxonomy_label": "özgün", "display_label": "özgün müzik", "aliases": ["özgün müzik", "ozgun muzik", "özgün"]},
+
+    {"id": "mood.aci", "category": "mood", "dimension": "mood", "taxonomy_label": "acı", "display_label": "acı", "aliases": ["acı", "aci"], "sync_search_terms": ["cathartic pain", "emotional intensity", "heartbreak drama"]},
+    {"id": "mood.huzun", "category": "mood", "dimension": "mood", "taxonomy_label": "hüzün", "display_label": "hüzün", "aliases": ["hüzün", "huzun"], "sync_search_terms": ["melancholy", "wistful sadness", "reflective longing"]},
+    {"id": "mood.ofke", "category": "mood", "dimension": "mood", "taxonomy_label": "öfke", "display_label": "öfke", "aliases": ["öfke", "ofke"], "sync_search_terms": ["anger", "defiance", "confrontation"]},
+    {"id": "mood.kabullenme", "category": "mood", "dimension": "mood", "taxonomy_label": "kabullenme", "display_label": "kabullenme", "aliases": ["kabullenme"], "sync_search_terms": ["resignation", "acceptance of fate", "weary resolve"]},
+    {"id": "mood.ironi", "category": "mood", "dimension": "mood", "taxonomy_label": "ironi", "display_label": "ironi", "aliases": ["ironi"], "sync_search_terms": ["irony", "sardonic", "bittersweet wit"]},
+    {"id": "mood.umut", "category": "mood", "dimension": "mood", "taxonomy_label": "umut", "display_label": "umut", "aliases": ["umut"], "sync_search_terms": ["hope", "optimism", "uplift"]},
+    {"id": "mood.ask", "category": "mood", "dimension": "mood", "taxonomy_label": "aşk", "display_label": "aşk", "aliases": ["aşk", "ask"], "sync_search_terms": ["romance", "devotion", "love"]},
+    {"id": "mood.heyecan", "category": "mood", "dimension": "mood", "taxonomy_label": "heyecan", "display_label": "heyecan", "aliases": ["heyecan"], "sync_search_terms": ["excitement", "momentum", "dance energy"]},
+    {"id": "mood.gurbet", "category": "mood", "dimension": "mood", "taxonomy_label": "gurbet", "display_label": "gurbet", "aliases": ["gurbet"], "sync_search_terms": ["exile longing", "diaspora", "homesickness"]},
+    {"id": "mood.nostaljik", "category": "mood", "dimension": "mood", "taxonomy_label": "nostaljik", "display_label": "nostaljik", "aliases": ["nostaljik"], "sync_search_terms": ["nostalgia", "memory", "looking back"]},
+
+    {"id": "instrument.baglama", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "bağlama", "display_label": "bağlama", "aliases": ["bağlama"]},
+    {"id": "instrument.ud", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "ud", "display_label": "ud", "aliases": ["ud"]},
+    {"id": "instrument.kanun", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kanun", "display_label": "kanun", "aliases": ["kanun"]},
+    {"id": "instrument.ney", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "ney", "display_label": "ney", "aliases": ["ney"]},
+    {"id": "instrument.darbuka", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "darbuka", "display_label": "darbuka", "aliases": ["darbuka"]},
+    {"id": "instrument.klarnet", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "klarnet", "display_label": "klarnet", "aliases": ["klarnet"]},
+    {"id": "instrument.electric_guitar", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "electric-guitar", "display_label": "electric guitar", "aliases": ["electric_guitar", "electric guitar"]},
+    {"id": "instrument.string_section", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "string-section", "display_label": "strings", "aliases": ["strings", "string-section"]},
+    {"id": "instrument.accordion", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "accordion", "display_label": "accordion", "aliases": ["accordion", "garmon"]},
+    {"id": "instrument.piano", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "piano", "display_label": "piano", "aliases": ["piano"]},
+    {"id": "instrument.cura", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "cura-bağlama", "display_label": "cura", "aliases": ["cura"]},
+    {"id": "instrument.electric_baglama", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "electric-bağlama", "display_label": "electric bağlama", "aliases": ["electric_baglama", "electric baglama", "electric bağlama"]},
+    {"id": "instrument.kemence_karadeniz", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "karadeniz-kemençesi", "display_label": "Karadeniz kemençesi", "aliases": ["kemence_karadeniz", "karadeniz kemençesi"]},
+    {"id": "instrument.kemence_klasik", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "klasik-kemençe", "display_label": "klasik kemençe", "aliases": ["kemence_klasik", "klasik kemençe"]},
+    {"id": "instrument.keman", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "keman", "display_label": "keman", "aliases": ["keman"]},
+    {"id": "instrument.mey", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "mey", "display_label": "mey", "aliases": ["mey"]},
+    {"id": "instrument.zurna", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "zurna", "display_label": "zurna", "aliases": ["zurna"]},
+    {"id": "instrument.kaval", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kaval", "display_label": "kaval", "aliases": ["kaval"]},
+    {"id": "instrument.def", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "def", "display_label": "def", "aliases": ["def"]},
+    {"id": "instrument.davul", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "davul", "display_label": "davul", "aliases": ["davul"]},
+    {"id": "instrument.kudum", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "kudüm", "display_label": "kudüm", "aliases": ["kudum", "kudüm"]},
+    {"id": "instrument.choir", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "choir", "display_label": "choir", "aliases": ["choir"]},
+    {"id": "instrument.backing_vocals", "category": "instrument", "dimension": "instrumentation", "taxonomy_label": "backing-vocals", "display_label": "backing vocals", "aliases": ["backing_vocals", "backing vocals"]},
+
+    {"id": "vocal.config.male", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "solo-male", "display_label": "male vocals", "aliases": ["male_vocals", "solo-male"]},
+    {"id": "vocal.config.female", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "solo-female", "display_label": "female vocals", "aliases": ["female_vocals", "solo-female"]},
+    {"id": "vocal.config.duet", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "duet-mf", "display_label": "duet", "aliases": ["duet", "duet-mf"]},
+    {"id": "vocal.config.instrumental", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "instrumental", "display_label": "instrumental", "aliases": ["instrumental"]},
+    {"id": "vocal.technique.hancere", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "hançere", "display_label": "hançere", "aliases": ["hancere", "hançere"]},
+    {"id": "vocal.technique.gazel", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "gazel", "display_label": "gazel", "aliases": ["gazel"]},
+    {"id": "vocal.technique.duz_okuyus", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "düz-okuyuş", "display_label": "düz okuyuş", "aliases": ["duz_okuyus", "düz-okuyuş", "düz okuyuş"]},
+    {"id": "vocal.technique.taverna", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "taverna-style", "display_label": "taverna vocal", "aliases": ["taverna_vocal", "taverna-style"]},
+    {"id": "vocal.technique.call_response", "category": "vocal", "dimension": "vocal_configuration", "taxonomy_label": "call-and-response", "display_label": "call-and-response", "aliases": ["call-and-response", "call_response"]},
+    {"id": "vocal.technique.belt", "category": "vocal", "dimension": "vocal_technique", "taxonomy_label": "bağırma", "display_label": "belt", "aliases": ["belt", "bağırma"]}
+  ],
+  "maest_hints": {
+    "Folk, World, & Country---Folk": ["genre.family.halk"],
+    "Folk, World, & Country---Laïkó": ["genre.family.fantezi", "genre.family.sanat"],
+    "Folk, World, & Country---Éntekhno": ["genre.family.ozgun", "genre.family.halk"],
+    "Folk, World, & Country---Hindustani": ["genre.family.halk"],
+    "Pop---Vocal": ["genre.family.pop", "genre.family.arabesk"],
+    "Pop---Ballad": ["genre.family.pop", "genre.family.fantezi"],
+    "Pop---Schlager": ["genre.family.fantezi", "genre.family.pop"],
+    "Pop---Chanson": ["genre.family.fantezi", "genre.family.pop"],
+    "Rock---Pop Rock": ["genre.family.rock"],
+    "Rock---Folk Rock": ["genre.subtype.anadolu_rock"],
+    "Rock---Prog Rock": ["genre.subtype.anadolu_psych_rock"],
+    "Rock---Psychedelic Rock": ["genre.subtype.anadolu_psych_rock"],
+    "Rock---Hard Rock": ["genre.family.rock"],
+    "Stage & Screen---Soundtrack": ["genre.family.pop"],
+    "Latin---MPB": ["genre.family.pop"]
+  }
+}