{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CEOOS62NTZKG4EILIB3DDD2QUL","short_pith_number":"pith:CEOOS62N","canonical_record":{"source":{"id":"2402.05856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-07T09:32:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c034dd3277d50f38ecb732b8c9e80f445cf638a606fa390acf01ff039ba00ab","abstract_canon_sha256":"82cc3f720ffd6a3929ec7845d5a60c2ad4ef235878545f3230258a98e3191879"},"schema_version":"1.0"},"canonical_sha256":"111ce97b4d9e546e110b4076318f50a2d36b9cd7cb91e773f6c43b3543d31176","source":{"kind":"arxiv","id":"2402.05856","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05856","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05856v1","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05856","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"CEOOS62NTZKG","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"CEOOS62NTZKG4EIL","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"CEOOS62N","created_at":"2026-07-05T07:43:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CEOOS62NTZKG4EILIB3DDD2QUL","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-07T09:32:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c034dd3277d50f38ecb732b8c9e80f445cf638a606fa390acf01ff039ba00ab","abstract_canon_sha256":"82cc3f720ffd6a3929ec7845d5a60c2ad4ef235878545f3230258a98e3191879"},"schema_version":"1.0"},"canonical_sha256":"111ce97b4d9e546e110b4076318f50a2d36b9cd7cb91e773f6c43b3543d31176","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:04.290970Z","signature_b64":"Ra9vbfwY1UDNVyPO3/lEu5uckaY4r844OBk3qIbH/pPqttyoTi1qUqOA4MMUVQhV5yfI2VthjyUK+oeAlu97DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111ce97b4d9e546e110b4076318f50a2d36b9cd7cb91e773f6c43b3543d31176","last_reissued_at":"2026-07-05T07:43:04.290585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:04.290585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05856","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":"2026-07-05T07:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMFvz0DsG0maqt77/fhfy15Mmv1WZW1KyNovkA83klJHEu+6Ywe+jtL7oF1qsPCTyCUMZuJpEGYzkabv5pSnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:43:40.146542Z"},"content_sha256":"d748cee5233dc075cc37c7486e61a6a0a5bf9af4c6b7a91ee360886e36fda6eb","schema_version":"1.0","event_id":"sha256:d748cee5233dc075cc37c7486e61a6a0a5bf9af4c6b7a91ee360886e36fda6eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CEOOS62NTZKG4EILIB3DDD2QUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure-Informed Protein Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Aur\\'elie Lozano, Jian Tang, Jiarui Lu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2024-02-07T09:32:35Z","abstract_excerpt":"Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05856","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/2402.05856/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":"2026-07-05T07:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6heCFXykStqmyeTCeQSNOGGpuZzZ9OMhjzX1fzjGc1LbuDdMAm2zDaoPj9t+Wci8sXFLeoqmG4qi0zAQpF6kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:43:40.146907Z"},"content_sha256":"a0d2370d1860c3e68adc67465d6f66fc12fc29dbc7848b7bd6540e19704e5c23","schema_version":"1.0","event_id":"sha256:a0d2370d1860c3e68adc67465d6f66fc12fc29dbc7848b7bd6540e19704e5c23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEOOS62NTZKG4EILIB3DDD2QUL/bundle.json","state_url":"https://pith.science/pith/CEOOS62NTZKG4EILIB3DDD2QUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEOOS62NTZKG4EILIB3DDD2QUL/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":"2026-07-14T19:43:40Z","links":{"resolver":"https://pith.science/pith/CEOOS62NTZKG4EILIB3DDD2QUL","bundle":"https://pith.science/pith/CEOOS62NTZKG4EILIB3DDD2QUL/bundle.json","state":"https://pith.science/pith/CEOOS62NTZKG4EILIB3DDD2QUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEOOS62NTZKG4EILIB3DDD2QUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CEOOS62NTZKG4EILIB3DDD2QUL","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":"82cc3f720ffd6a3929ec7845d5a60c2ad4ef235878545f3230258a98e3191879","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-07T09:32:35Z","title_canon_sha256":"1c034dd3277d50f38ecb732b8c9e80f445cf638a606fa390acf01ff039ba00ab"},"schema_version":"1.0","source":{"id":"2402.05856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05856","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05856v1","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05856","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"CEOOS62NTZKG","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"CEOOS62NTZKG4EIL","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"CEOOS62N","created_at":"2026-07-05T07:43:04Z"}],"graph_snapshots":[{"event_id":"sha256:a0d2370d1860c3e68adc67465d6f66fc12fc29dbc7848b7bd6540e19704e5c23","target":"graph","created_at":"2026-07-05T07:43:04Z","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/2402.05856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal c","authors_text":"Aur\\'elie Lozano, Jian Tang, Jiarui Lu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-07T09:32:35Z","title":"Structure-Informed Protein Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05856","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:d748cee5233dc075cc37c7486e61a6a0a5bf9af4c6b7a91ee360886e36fda6eb","target":"record","created_at":"2026-07-05T07:43:04Z","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":"82cc3f720ffd6a3929ec7845d5a60c2ad4ef235878545f3230258a98e3191879","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-07T09:32:35Z","title_canon_sha256":"1c034dd3277d50f38ecb732b8c9e80f445cf638a606fa390acf01ff039ba00ab"},"schema_version":"1.0","source":{"id":"2402.05856","kind":"arxiv","version":1}},"canonical_sha256":"111ce97b4d9e546e110b4076318f50a2d36b9cd7cb91e773f6c43b3543d31176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"111ce97b4d9e546e110b4076318f50a2d36b9cd7cb91e773f6c43b3543d31176","first_computed_at":"2026-07-05T07:43:04.290585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:04.290585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ra9vbfwY1UDNVyPO3/lEu5uckaY4r844OBk3qIbH/pPqttyoTi1qUqOA4MMUVQhV5yfI2VthjyUK+oeAlu97DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:04.290970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d748cee5233dc075cc37c7486e61a6a0a5bf9af4c6b7a91ee360886e36fda6eb","sha256:a0d2370d1860c3e68adc67465d6f66fc12fc29dbc7848b7bd6540e19704e5c23"],"state_sha256":"c65cd84e656ea39c4737b3d1e964362d8a476cf16adc1809ccb9bafb2031d90c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCkXs5KSjosTVQz/8gyjdm3O3ZlMsgtFuUsVT2Q8AKpMj61XM11dN0Xd4yZtkxOnZefr9od1+DA/1G/9EZhgBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T19:43:40.149330Z","bundle_sha256":"2bf6a2615857783ac91735e5e556af1f5d4484e627a5a9f496aa8b4b1f1f751e"}}