| a7d0dbe3088ee22e14bd9e1d1ddf56ba4efbb7c8a79ae59e309787ba604e5a09 .gitattributes |
| a6cba85bc92e0cff7a450b1d873c0eaa2e9fc96bf472df0247a26bec77bf3ff9 LICENSE |
| da124040868d09023b0cf8babe348d153300fb1a91db31c625d8873c1a3c0142 MANIFEST.md |
| 209bf0a55525d3f3d3f3b4e4efe1c110662ac7eac24df94511a146a005b6d730 README.md |
| 7c395b48f5234602ff8f5e12adb1e24932d460a05dfa522ba3ae245d15f469a1 RELEASE_AUDIT.md |
| 7286c5016e3b03dda7b49d852bcea37722b3ba9028f3715af35c708bab3e1051 code/affinose/README.md |
| bdeef1f7f1ef86f10e36fb75105d5a298a6d0af76041adab60605430cc6377d0 code/benchmarks/calculate_rankings.py |
| 07e21e7ec893453bf60a805abda0f177592d10dbf7af28dd609c763f35c68d4d code/benchmarks/consolidate_results.py |
| 0a89c7023819b257667503fca21413edd363a1a46130c8f244fd445c6e4b3bc5 code/benchmarks/create_excluded_dataset.py |
| 733b59a2e30cc79f2a80325fec89c300d634fd385f784e03e229dabc56679223 code/benchmarks/extract_all_benchmark_results.py |
| 77a6da4fdf3bb64fa03a497d66fafbcc960a274143afab8e6c8cdaec7910330e code/benchmarks/finetune.py |
| ded1b4465589277696b82a8c07793ecf89df22ea55660dfc19929b71df21e8b2 code/bertint/bertint_v8.py |
| fb71ce05800afc92ec2e5340d48e78db7d683529c3f0448e401f5c90bca42b3b code/bertint/bertint_v8_inference.py |
| 9d9bd389ffc1080254df2f824b6cd63dc0e58f8b31988193cb270ff6909a3da2 code/bertint/build_combined_dataset.py |
| d0932c17c7a3fd3e794e26945e673aca258a74388ec27d5935ba8b73209c6616 code/bertint/compare_ablation.py |
| 2a6a2a6c587959c27e4ee3ea03d49fd26b54ed271c6e58e42b8a3eb4fe9d53c9 code/bertint/dataset_v8.py |
| 76af1c59ca8f2bee013f159627cc0f1c5d8c7d02ef7963d0581e9a0d0d5a7886 code/bertint/generate_glycan_splits.py |
| e2f07603c56c1a86c3cdeae38709143153659a82669bcd3cf939934660cc4c70 code/bertint/training_v8.py |
| 8847ce63f55a7abdf804b6f59047adfc46a742ae094ecc91cce270a77813ffe7 code/contrastive/contrastive_trainer_v51_FINAL.py |
| 8615ad2346698d8a88c68f7fc0fe1e6befe275e75e38a3fb435f90f5519771f8 code/contrastive/contrastive_trainer_v5_SIMPLE.py |
| 4a09eeb3da4bdafe2d0b9cc41119c9a2a6ef0313b8ae018f18b4300023f61661 code/contrastive/extract_resolved_glycans.py |
| 21c9a3cd2e806aadacc0b7f1a0c3372d21a9d3dd6d2dbfcf7a701fa6855979d5 code/contrastive/generate_negatives_v4_FINAL.py |
| 3fc781ab69ef520f84fcc8d903feed1ba26e63c1b568b57739b659e5745cf071 code/contrastive/mcns_filter_75k_v3_FINAL.py |
| da2e46dde0650c184a2cef12ca7384b86939481200211493e73a751700a783e8 code/contrastive/score_negative_difficulty.py |
| effcd06f210a78de9102c30b1d523e9720d6db396b2d9c020fee25c81641b9ce code/contrastive_training/step3_train_v51_FIXED_FINAL.sh |
| d2d03599259773809ee98eb23104a12bade74efd40c371b19ee40c828c6c6e65 code/data_processing/augment_pretraining_data.py |
| 40c97be90a30b18fd489fcf3ab7f314d39afae06096ef72311f224d98b9ca23b code/data_processing/convert_iupac_glycosmos.py |
| e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 code/downstream_tasks/__init__.py |
| e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 code/downstream_tasks/utils/__init__.py |
| 3c281211bcf706200ce2614e6810300405db11f0e81bf07ffb6a1d460e9b0b16 code/downstream_tasks/utils/baseline_results.py |
| d6ce62d2b163e446abf9e1df2cdd6268012063d7667f9198083c805b1f4be35b code/downstream_tasks/utils/dataset.py |
| d8135231ff7dc8b9754540bf8c9f37ef02fbb57560e07f8585fc445c6ae4fb22 code/downstream_tasks/utils/tokenizer.py |
| 0bc54399362945601bcfd403441fc80968d173200dd0561f57568b2053a94839 code/downstream_tasks/utils/wurcs_bpe_tokenizer.py |
| de8c3237b858b640ee9fbf4dac34864c54b6dac80bc89f346a44c774254289a4 code/model/__init__.py |
| b50d50d6ae50d520e6834563892bfc00fc11c5bb1322a84abf84ae4d97c895dd code/model/dataset.py |
| 1c141c552efd6e0f58da70bd06290d352ad2a23bd3a62246a9f0bf77e58b8a11 code/model/enhanced_classifier.py |
| b69f14c9976951325e3a0a4e8107a16126e67d410e966650f513f1f538a732bb code/model/glycan_bert.py |
| 91e5e235d04c332251ccb85969396746ab68f1ebbc50c4f6611b86cd8d1e9de9 code/model/hierarchical_glycan.py |
| 8e06c32f4e844c3c66f146fd15a075472808a0720c892d0b9683dfd32f15ef0c code/model/multimodal_glycan_bert_v3.py |
| d8135231ff7dc8b9754540bf8c9f37ef02fbb57560e07f8585fc445c6ae4fb22 code/model/tokenizer.py |
| 0bc54399362945601bcfd403441fc80968d173200dd0561f57568b2053a94839 code/model/wurcs_bpe_tokenizer.py |
| 1746be26e253607c316339f4f12ccca2382114018a2034e79ee307b29bcebebd code/probes/analyze_core_biology.py |
| fe3eaa0abe0d505d4612a213ffcede4702ef6f57d674303e273f8f555d6f68e7 code/probes/analyze_embeddings.py |
| 20ec31c3f98eeb364be6c807749799221def9a1ac08db4a53984bcb436f98d41 code/probes/cluster_scripts/run_benchmark_embeddings.sh |
| 9f43159886b13baf03090b90f3d8cfc8559a75bf43c0e4d39a01912104b57e7f code/probes/cluster_scripts/run_diag_zero.sh |
| 5511e16507a3b4dadf2450b1b7befd4d49dd343f1f18501e54ae0797a55cddfd code/probes/cluster_scripts/run_embedding_analysis.sh |
| 586f7b1c86bf1744b4518ffab8f97b9a4772d1ce05c618c4e15dbe1fb5c07e3c code/probes/cluster_scripts/run_explore_bio.sh |
| b8be7a2ecb16a7a6564ffc6e076f4a90ccd726e007dbba6a26629600b62f6219 code/probes/cluster_scripts/run_novel_probes.sh |
| bca6d50202b4cd5172c4d08ed657cf68d9db66d17d52d2bdd3562e792a3d65a3 code/probes/cluster_scripts/run_novel_probes_v2.sh |
| f9bfd3aca393cc814e504ec5d3f0567d887988f036c9b93a4c42d4377a8e9c9e code/probes/cluster_scripts/run_novel_probes_v2_full.sh |
| bb7f95112706f70f55ab02803b36160301554889dabe2c42df1b23e562d17c70 code/probes/cluster_scripts/run_probe10_lectin.sh |
| 6f958951b3b9c7a38e78b48b91883dd54f392fbd5d2a8ed1d8e47ce7e5bf32b5 code/probes/cluster_scripts/run_probe10_v2.sh |
| 07f769ffe725740ef03e93bd422372427b7ad4822c0159f5d5979746c7cf2999 code/probes/cluster_scripts/run_probe14.sh |
| 3c8cfbe889fc9a18056fb31b360fd8a65102c35636cb8b5f673f623321f1bb75 code/probes/cluster_scripts/run_probe15.sh |
| e0889a94fd1ddec0ebf3960f3cfc463e8c1b6c4259a10923506f174ba225ec85 code/probes/cluster_scripts/run_probe15c2.sh |
| a0b090992e2a52954c1d353367aaaadfead6c7f01087fc9fa656985f7f6fb62a code/probes/cluster_scripts/run_probe15d.sh |
| 104ba71c0d0a874313449d5c9778d06d5062b0c530e153329262860565102c5b code/probes/cluster_scripts/run_probe15h.sh |
| daeced8da52e9802b72d1d8590acd074667c04bbf0dd4fc0aa2fae681766f5cd code/probes/cluster_scripts/run_probe2_layerwise.sh |
| 0429b6669df38c0942a50265112036db5a6e8d7662476606df4c8cd6715c6afd code/probes/cluster_scripts/run_probe3_4.sh |
| f369238fff347a0d2bfd5dd2308f85fcb778d558a3ef3cd535073f3726c485b4 code/probes/cluster_scripts/run_probe4_filtered.sh |
| c9e145766037a636aaacfde275783aaef07c53d5b542a82202854ef770e90727 code/probes/cluster_scripts/run_probe8.sh |
| a26edb399226db8e5f12c8ffba7909befefc5385f21702cccb4d9a458e2e9ace code/probes/cluster_scripts/run_probe9_biosynthesis.sh |
| de009efa3c191da5d1c0f4372fe4988b255ea0fb177e5b0aeca4e6f39c9184f4 code/probes/cluster_scripts/run_probes_expanded_resolved_v5.sh |
| 072be6b54439152825e15f48070beaa061d852d79128a1f1444c080157b1fd52 code/probes/cluster_scripts/run_probes_expanded_resolved_v6.sh |
| 6e4af060737706f29a3524db7e67b8d0964c62a9b4b90cb629b1d294cb4347e0 code/probes/cluster_scripts/run_probes_expanded_v5.sh |
| 882ef75b29f7b979b99f74df8c8fc2d9a889f0bfdce1c46ecc3532a3cf89efd5 code/probes/cluster_scripts/run_probes_expanded_v6.sh |
| c454aefad7b6d39070c2b83b0c988d9388e5d938d690f39db5485e00dc587226 code/probes/cluster_scripts/run_probes_glyco_immuno.sh |
| 10f8f313a9d80e2eac9f89534298f040dd809cd71023f5db66144570f2665849 code/probes/cluster_scripts/run_probes_resolved_v5.sh |
| 1f4efc28840a2a0901d9c861bcf7f6edd6c507d6f53c5272d6282728874d3f41 code/probes/cluster_scripts/run_probes_resolved_v6.sh |
| e31d4ba5fac34a4bc6ada48d129f9d301a6ea0e24b7f2da6383c0007cad7e3ed code/probes/cluster_scripts/run_probes_v5_full_cached.sh |
| c4134ae3d7189087fb3f047957443713a932ceda885465747f6d62b8057bd934 code/probes/cluster_scripts/run_probes_v5_full_external.sh |
| 3d8f7046b56584c0dc7c44cdee25e324a23175f0fb744735f3796a2ef79b1784 code/probes/cluster_scripts/run_probes_v5_res_cached.sh |
| 3c24e6d7a5a0657b884bb9658c87871a580ca8437080bd95a08e495bced4222b code/probes/cluster_scripts/run_probes_v5_res_external.sh |
| 17faa873c11dd5939737305502c9f0b247e20383be02dc7cdc1d2eacd63dae52 code/probes/cluster_scripts/run_probes_v6_full_cached.sh |
| 960792a133f0e832063f196b6b882a0a974e2eb2a9fa3c33233db07ab851bde5 code/probes/cluster_scripts/run_probes_v6_full_external.sh |
| 5cced03d48008b8d7b66cf9138d59a97fd387dbf8c9b0a906fece046cd4aa050 code/probes/cluster_scripts/run_probes_v6_res_cached.sh |
| 16dc0edb0076db41a6db44bd85c06ebeae98c77d406bb6e38f7e64ba2bc903fa code/probes/cluster_scripts/run_probes_v6_res_external.sh |
| 43b433149b8d30bcaee818abff95a9ab0047d15c11a55944a3638ff3d97b60ac code/probes/cluster_scripts/run_tier2_biology.sh |
| 2182320665a2021d7180fdf0ba6bb131d8592777d312d6cc9b59421de33fbf5e code/probes/cluster_scripts/run_tsne_figure.sh |
| 08300f1cffed393016bae0fc9e59be5e9d987eaaee244c452427babca6e2c3a8 code/probes/cluster_scripts/run_v6_training.sh |
| 6e51b94aa6bf4960fe12e362e29101f3f143104e1eaed7016376d486be83250d code/probes/embed_benchmark_tasks.py |
| 95ebff8cbd5e6028cfb8a668361d0bcc236c36da42995b0f13afa150993b0548 code/probes/extract_embeddings.py |
| cec43a83d95ed25b29d365c11156a653e72c6775329e8e4070ecf2e2a3bdb1c2 code/probes/novel_probes_v2.py |
| 30c74d07267f34a077c663d844764ccf07eac28becab727b9da1dd952a737647 code/probes/probe_01_tsne_clustering.py |
| 1d39a5e442b0d1327c6b1a48c952c08457988afd46f5a5d7828a61a72a340851 code/probes/probe_10_lectin_motifs.py |
| 4dcd35b2acaec555a32df5a6e1ff70504240facb9b8759e48e16050f77c73f3c code/probes/probe_10_tissue_presence.py |
| dd868142857074cd9bf638c97566e43423186fe328c8300dd4ae1cb74bf0247d code/probes/probe_14_retrieval.py |
| 06fca4190c5b8622093cc48ed3c6bd10df70576273aa7f3879a3c09261a03990 code/probes/probe_15_seal_milk_ood.py |
| ebaa15252c3d3ac28a288ff7b78493134a49260398bb7b18ee3a351be06c1f4f code/probes/probe_15h_phylogenetic.py |
| 4bb6ac7f62d7ab3f2d6313dc8437e947f0231c984d23b324688b9760113f1a69 code/probes/probe_2_layerwise_cls.py |
| a4f259e8d00daf702b0b4ab32dc6e2cb3bf99b4c46f2c028e12b0c857b70e424 code/probes/probe_3_4_attention_structure.py |
| 831800db52a0373a98534636c8fd3aced8719ac4dcd86160bccd3a66093d2caf code/probes/probe_7_contrastive_ablation.py |
| 76b53cb05c2350de8871293684006ce389bcbfde5891d8d34233bad40513320c code/probes/probe_8_disease_tissue.py |
| 0b184b387f1ec95623a84dfc1ecd43e816c47608bc23311f1b070e9c06cc3641 code/probes/probe_9_biosynthesis_order.py |
| 7d9edcfe426301f78a0c7a80c51688b19b01776b31f950d7250cea60215f511f code/probes/probe_exploratory_biology.py |
| 6e63f181f22987e3c6f926990a2ff1892cee08ca5709d1a6925d8f942117ee69 code/tokenizer/generate_bpe_ambiguity.py |
| 0d967082a8225a1eab98315c2fe7916eff0e863ec04287a43351b757e08f5070 code/training/__init__.py |
| 09014d0945b12f3ef4dc4656cade1e4cd55ede7e3d816c7106ce0a2c45c0a49a code/training/analyze_confidence.py |
| f0c8efda7a12942b4c6359792d6ee9417e6a9ec0eb04623ad17b4772430270b5 code/training/ipa_bpe_distillation.py |
| bbb9e5b156591285a2e2a052261d9215771659cb082dd802a39fed00958ad1fd code/training/masking.py |
| 54faea0a20d16e20da46775d0562eb2a9b8d7979ee6c43c0f26b4d326d24d5fc code/training/multimodal_dataset.py |
| ce660a7a7dccb88e52fefbc87edd36c8e0ca247fbe896aeaa22079dc4c475970 code/training/multimodal_masking.py |
| 3bd7ecacf93b5e5d9d40a8ad9d2a0e8377ab05f3d2ad6b64a910fc904be5e20c code/training/train_multimodal.py |
| 848d001b28c35151b91d6cc986e595f71c4042da6d1c7238bc67fa64258b829e code/training/train_wurcs_bpe.py |
| eff37151a2bfdc196d93f854c82262bd9a65ec03760c0a4e75a5355e0e2a7e52 configs/multimodal_config_v3_ORIGINAL.yaml |
| 84f6c73262fad6d2fdb2d5e5bca0f7fcd1ee8b2d98c4d83c3f0731bc813d3e51 configs/multimodal_config_v4_bpe.yaml |
| 6f83ac0fb29df3b579763a79350b3ed762b4dcd0dfc1b36ee41350fcd189b1d8 configs/multimodal_config_v5a_bpe_topo.yaml |
| 7f6a405d725e7a67877360bacdf3d6bc97d0fbdbbee315b4d84c9dc62fba2a22 configs/multimodal_config_v5b_excluded.yaml |
| 0d4e950f592fefd8a03e7d42ab037f751c94de9f5503ff1391ec1b2c878e9163 data/splits/complete_exclusion_list.txt |
| 37decf0099e54c883fd4d05a8298ee09547b9ccc0060a1314a9f55fae64258af data/splits/train_val_split.json |
| 417fc41a53bd9849d686b5bb7ac2c5ffcdb73f793f97d156c7f0f214e438af80 data/vocab/ambiguity_tokens_CORRECTED.json |
| c68cd003370b2dcdb162f848f766e4e62f2653c6c38d205f8cbe53a9aabe2d74 data/vocab/bpe_ambiguity_tokens.json |
| 6a572afdf53f1494ab96c896876b824ca7ea749777352606aa9f96bf270ceecc data/vocab/bpe_vocabulary.json |
| 6a572afdf53f1494ab96c896876b824ca7ea749777352606aa9f96bf270ceecc data/vocab/bpe_vocabulary_clean.json |
| 044030f212648a98fc477352328651c284d185660d9a2a7116f92f73f97e1ae5 data/vocab/confidence_analysis.json |
| ff7bb6a3de636dbee79846ef8083bdab004e9b79cd60715fbe1474d482e119c8 data/vocab/ms_vocabulary.json |
| f315117a51a49e4019812367e72423620c007c9c73bf6e19f357fe4ca395de3a data/vocab/vocabulary.json |
| 820ecfca39cd6311e0499b3c4bef36708ae6cb6e536d86a629e524515ad17d66 provenance/CORPUS_PIPELINE_AND_TOKENIZER_PROVENANCE_2026-04-19.md |
| 670fa0cdd66ca2b21132545a196924723b6ec0943df0bff7e7540731564a7eed provenance/SOURCE_LOG.md |
| b4b19a7d28f543f36bbca2b3ab5444bdafc01e0b173c57faccc79f8bf3e78d2e provenance/compute_provenance/CLUSTER_VERIFIED_MODEL_LINEAGE_20260419.md |
| 0eadc9e9c8e1354e9b5f696f6d80b7257e8e7ed2d4280b389d7bfd1cf46fc750 provenance/compute_provenance/COMPUTE_PROVENANCE_LOG.md |
| 445408075a619e10f1511cbf13d6540f020fe5a238a11f05e83e34adeecea096 provenance/compute_provenance/EXA_SCALABILITY_MAIN_TEXT_FILL_20260419.md |
| c762eea25d0e7537363a02e8bb4f5b0d6eea7e558b76574731b536b32121060b provenance/compute_provenance/compute_runtime_summary.csv |
| 838301cb054463d81af4488a9f3e7d8eec13fcf7e860665202f701711458efd2 provenance/compute_provenance/compute_runtime_summary.json |
| b3882871574b41505c6f46fdc7dbdc716249713e9173715649d591f897dc564d provenance/compute_provenance/launch_script_summary.csv |
| ddc06ca59280bc75410aefa73816e9a6809e7720a6ec3b43198fa99c503d88c1 provenance/compute_provenance/multimodal_config_v5b_cluster_copy.yaml |
| 04d9c188cbd8a2a7bf68349967a0472f33a5f9ee37c7de1f867eec5120979bcd provenance/compute_provenance/run_train_v5b_cluster_verified_copy_20260201.sh |
| 59adc26c35d55c259411d5bd49177bfce0f4269d96184d5c4dbb1f334fc54bf2 provenance/compute_provenance/step3_contrastive_train_cluster_verified_copy_20260130.sh |
| 21260131d5625b086b3ddd73a701296378dd38ee5c1b383c602ef207bdea9889 requirements.txt |
|
|