{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3HMCMAW4LMK2SAYSI6YWROJNM7","short_pith_number":"pith:3HMCMAW4","schema_version":"1.0","canonical_sha256":"d9d82602dc5b15a9031247b168b92d67d7fc2b73caa74de0f047d923876cfd04","source":{"kind":"arxiv","id":"2506.07035","version":1},"attestation_state":"computed","paper":{"title":"AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Renjing Xu, Zixuan Jiang","submitted_at":"2025-06-08T07:59:09Z","abstract_excerpt":"Deciphering protein function remains a fundamental challenge in protein representation learning. The task presents significant difficulties for protein language models (PLMs) due to the sheer volume of functional annotation categories and the highly imbalanced distribution of annotated instances across biological ontologies. Inspired by the remarkable success of reinforcement learning from human feedback (RLHF) in large language model (LLM) alignment, we propose AnnoDPO, a novel multi-modal framework for protein function prediction that leverages Direct Preference Optimization (DPO) to enhance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-08T07:59:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74b2a963033f42c131582408f70a70c8cb5974fa1ac48a8b50639f9e7db93308","abstract_canon_sha256":"076dd117998f67c1159470c0ec2f7050991761613e3128dea6375852c5497e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:00.100799Z","signature_b64":"9h3K2dzEaDDEGM5hHAuEIw0JQMY+Gll5V2XphsJdNJgrlQpPdQRK/XNJM8KUMcksXMKoySJjdKXV4rlPoY2VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9d82602dc5b15a9031247b168b92d67d7fc2b73caa74de0f047d923876cfd04","last_reissued_at":"2026-07-05T11:18:00.100341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:00.100341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Renjing Xu, Zixuan Jiang","submitted_at":"2025-06-08T07:59:09Z","abstract_excerpt":"Deciphering protein function remains a fundamental challenge in protein representation learning. The task presents significant difficulties for protein language models (PLMs) due to the sheer volume of functional annotation categories and the highly imbalanced distribution of annotated instances across biological ontologies. Inspired by the remarkable success of reinforcement learning from human feedback (RLHF) in large language model (LLM) alignment, we propose AnnoDPO, a novel multi-modal framework for protein function prediction that leverages Direct Preference Optimization (DPO) to enhance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07035","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/2506.07035/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07035","created_at":"2026-07-05T11:18:00.100414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07035v1","created_at":"2026-07-05T11:18:00.100414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07035","created_at":"2026-07-05T11:18:00.100414+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HMCMAW4LMK2","created_at":"2026-07-05T11:18:00.100414+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HMCMAW4LMK2SAYS","created_at":"2026-07-05T11:18:00.100414+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HMCMAW4","created_at":"2026-07-05T11:18:00.100414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7","json":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7.json","graph_json":"https://pith.science/api/pith-number/3HMCMAW4LMK2SAYSI6YWROJNM7/graph.json","events_json":"https://pith.science/api/pith-number/3HMCMAW4LMK2SAYSI6YWROJNM7/events.json","paper":"https://pith.science/paper/3HMCMAW4"},"agent_actions":{"view_html":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7","download_json":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7.json","view_paper":"https://pith.science/paper/3HMCMAW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07035&json=true","fetch_graph":"https://pith.science/api/pith-number/3HMCMAW4LMK2SAYSI6YWROJNM7/graph.json","fetch_events":"https://pith.science/api/pith-number/3HMCMAW4LMK2SAYSI6YWROJNM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7/action/storage_attestation","attest_author":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7/action/author_attestation","sign_citation":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7/action/citation_signature","submit_replication":"https://pith.science/pith/3HMCMAW4LMK2SAYSI6YWROJNM7/action/replication_record"}},"created_at":"2026-07-05T11:18:00.100414+00:00","updated_at":"2026-07-05T11:18:00.100414+00:00"}