{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JW24JOYSN4KKVMWAS63SY2SYPP","short_pith_number":"pith:JW24JOYS","canonical_record":{"source":{"id":"2503.08764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T17:57:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d71d90763655e4d8c237bc8e91bdd095b0d7804b92d271660c4f0f1e9401edf","abstract_canon_sha256":"1e181656210ae0fd5fadbe736fd32ee356814941aece24945acaa61384c73767"},"schema_version":"1.0"},"canonical_sha256":"4db5c4bb126f14aab2c097b72c6a587bf94ee2d345091158920c9cdce7805487","source":{"kind":"arxiv","id":"2503.08764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08764","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08764v1","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08764","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"JW24JOYSN4KK","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"JW24JOYSN4KKVMWA","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"JW24JOYS","created_at":"2026-07-05T10:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JW24JOYSN4KKVMWAS63SY2SYPP","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T17:57:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d71d90763655e4d8c237bc8e91bdd095b0d7804b92d271660c4f0f1e9401edf","abstract_canon_sha256":"1e181656210ae0fd5fadbe736fd32ee356814941aece24945acaa61384c73767"},"schema_version":"1.0"},"canonical_sha256":"4db5c4bb126f14aab2c097b72c6a587bf94ee2d345091158920c9cdce7805487","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:39.988676Z","signature_b64":"J8uYVcbrm/3CKRt9kBIs9JYsOCGs5CI/8D1wlcIbpoVShI0SuKyPhSV7rkn+jO8DE/9pdPhfdlhpBTv7XcDhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db5c4bb126f14aab2c097b72c6a587bf94ee2d345091158920c9cdce7805487","last_reissued_at":"2026-07-05T10:29:39.988098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:39.988098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08764","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwLl4fwzeZns6OeCKX6FlBGOtP8GWBaQtF3U1pTLSRf84VNkIXLzGpjNABvp4gwrR8huVBYm1+vJ1NeoC/ZnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:10:31.707316Z"},"content_sha256":"33ce635db8de163a182529e64091b65a33ba96b2bbef28be9efc032cfaf08fef","schema_version":"1.0","event_id":"sha256:33ce635db8de163a182529e64091b65a33ba96b2bbef28be9efc032cfaf08fef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JW24JOYSN4KKVMWAS63SY2SYPP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Interpretable Protein Structure Prediction with Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"David J. Yang, John J. Yang, Nithin Parsan","submitted_at":"2025-03-11T17:57:29Z","abstract_excerpt":"Protein language models have revolutionized structure prediction, but their nonlinear nature obscures how sequence representations inform structure prediction. While sparse autoencoders (SAEs) offer a path to interpretability here by learning linear representations in high-dimensional space, their application has been limited to smaller protein language models unable to perform structure prediction. In this work, we make two key advances: (1) we scale SAEs to ESM2-3B, the base model for ESMFold, enabling mechanistic interpretability of protein structure prediction for the first time, and (2) w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08764","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.08764/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uBXSp6g0sLtsL67tu/ho+FwxtuZY6M1e0gpIOHAGXfFRRyjNZ4WZ3tL4pI++XADBBD9rKfEgKvXGOhclN2lBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:10:31.707809Z"},"content_sha256":"7d60b0c728cb0d0b1829f0feb8f3157c1ec1175f8de673472d8d66cbd1deaa55","schema_version":"1.0","event_id":"sha256:7d60b0c728cb0d0b1829f0feb8f3157c1ec1175f8de673472d8d66cbd1deaa55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW24JOYSN4KKVMWAS63SY2SYPP/bundle.json","state_url":"https://pith.science/pith/JW24JOYSN4KKVMWAS63SY2SYPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW24JOYSN4KKVMWAS63SY2SYPP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T15:10:31Z","links":{"resolver":"https://pith.science/pith/JW24JOYSN4KKVMWAS63SY2SYPP","bundle":"https://pith.science/pith/JW24JOYSN4KKVMWAS63SY2SYPP/bundle.json","state":"https://pith.science/pith/JW24JOYSN4KKVMWAS63SY2SYPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW24JOYSN4KKVMWAS63SY2SYPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JW24JOYSN4KKVMWAS63SY2SYPP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1e181656210ae0fd5fadbe736fd32ee356814941aece24945acaa61384c73767","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T17:57:29Z","title_canon_sha256":"1d71d90763655e4d8c237bc8e91bdd095b0d7804b92d271660c4f0f1e9401edf"},"schema_version":"1.0","source":{"id":"2503.08764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08764","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08764v1","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08764","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"JW24JOYSN4KK","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"JW24JOYSN4KKVMWA","created_at":"2026-07-05T10:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"JW24JOYS","created_at":"2026-07-05T10:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:7d60b0c728cb0d0b1829f0feb8f3157c1ec1175f8de673472d8d66cbd1deaa55","target":"graph","created_at":"2026-07-05T10:29:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.08764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models have revolutionized structure prediction, but their nonlinear nature obscures how sequence representations inform structure prediction. While sparse autoencoders (SAEs) offer a path to interpretability here by learning linear representations in high-dimensional space, their application has been limited to smaller protein language models unable to perform structure prediction. In this work, we make two key advances: (1) we scale SAEs to ESM2-3B, the base model for ESMFold, enabling mechanistic interpretability of protein structure prediction for the first time, and (2) w","authors_text":"David J. Yang, John J. Yang, Nithin Parsan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T17:57:29Z","title":"Towards Interpretable Protein Structure Prediction with Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08764","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:33ce635db8de163a182529e64091b65a33ba96b2bbef28be9efc032cfaf08fef","target":"record","created_at":"2026-07-05T10:29:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1e181656210ae0fd5fadbe736fd32ee356814941aece24945acaa61384c73767","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T17:57:29Z","title_canon_sha256":"1d71d90763655e4d8c237bc8e91bdd095b0d7804b92d271660c4f0f1e9401edf"},"schema_version":"1.0","source":{"id":"2503.08764","kind":"arxiv","version":1}},"canonical_sha256":"4db5c4bb126f14aab2c097b72c6a587bf94ee2d345091158920c9cdce7805487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4db5c4bb126f14aab2c097b72c6a587bf94ee2d345091158920c9cdce7805487","first_computed_at":"2026-07-05T10:29:39.988098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:39.988098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J8uYVcbrm/3CKRt9kBIs9JYsOCGs5CI/8D1wlcIbpoVShI0SuKyPhSV7rkn+jO8DE/9pdPhfdlhpBTv7XcDhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:39.988676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ce635db8de163a182529e64091b65a33ba96b2bbef28be9efc032cfaf08fef","sha256:7d60b0c728cb0d0b1829f0feb8f3157c1ec1175f8de673472d8d66cbd1deaa55"],"state_sha256":"177a70950096043274720b754b1d18e8484ffd9e3bcce497d8eb20402374b31d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxhEypeGVEj1WLF4e6lbxS0FELf4AY26EKyHr65llmDhTDgsULbpCCq+lekahrLxUa3GiILigm4aaUk13+MLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:10:31.711056Z","bundle_sha256":"5f7a1b428ddddbb45aaaffdc1ff5865c5cd4995fa0c43c1e386ac6b51c3521d6"}}