{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6CAF4ZWYNBT2VA4M3ITC2ROQ3J","short_pith_number":"pith:6CAF4ZWY","schema_version":"1.0","canonical_sha256":"f0805e66d86867aa838cda262d45d0da6b191f50b21b940fd48bcb27e754c415","source":{"kind":"arxiv","id":"2606.04228","version":1},"attestation_state":"computed","paper":{"title":"When Does Structure Help? The Information Bonus of AlphaFold2 Representations over Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Kargi Chauhan","submitted_at":"2026-06-02T21:26:09Z","abstract_excerpt":"AI scientist systems increasingly choose biological foundation models before they choose experiments. In protein pipelines, this creates a concrete engineering and scientific question: when is the cost of structural inference worth paying over a cheaper sequence-only model? We introduce the information bonus (IB), a task-level metric that measures the linearly accessible advantage of frozen single-sequence AlphaFold2 Evoformer representations over frozen ESM-2 embeddings under protein-level cross-validation. Across binding affinity regression (PDBbind, n=5,680), conformational flexibility (ATL"},"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":"2606.04228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2026-06-02T21:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"beff974617ba20b94162f7c68bbb1c7afa6ac957d370e91e7eac9e6065b7e8de","abstract_canon_sha256":"9f7a7ef4f5349d6a4c6b3291d1942c7884f37467bbb44ef160b1dff25dbb94c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:59.251963Z","signature_b64":"RdaaBWxiJg11mKR+BV327iGhOmUA3TA6zgDbRQuOu9mTLQbOhq4yfcRcX4P7aj/bCtNAgVwSD4oYd+VSinK8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0805e66d86867aa838cda262d45d0da6b191f50b21b940fd48bcb27e754c415","last_reissued_at":"2026-06-04T01:08:59.251479Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:59.251479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Structure Help? The Information Bonus of AlphaFold2 Representations over Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Kargi Chauhan","submitted_at":"2026-06-02T21:26:09Z","abstract_excerpt":"AI scientist systems increasingly choose biological foundation models before they choose experiments. In protein pipelines, this creates a concrete engineering and scientific question: when is the cost of structural inference worth paying over a cheaper sequence-only model? We introduce the information bonus (IB), a task-level metric that measures the linearly accessible advantage of frozen single-sequence AlphaFold2 Evoformer representations over frozen ESM-2 embeddings under protein-level cross-validation. Across binding affinity regression (PDBbind, n=5,680), conformational flexibility (ATL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04228","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/2606.04228/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":"2606.04228","created_at":"2026-06-04T01:08:59.251547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04228v1","created_at":"2026-06-04T01:08:59.251547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04228","created_at":"2026-06-04T01:08:59.251547+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CAF4ZWYNBT2","created_at":"2026-06-04T01:08:59.251547+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CAF4ZWYNBT2VA4M","created_at":"2026-06-04T01:08:59.251547+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CAF4ZWY","created_at":"2026-06-04T01:08:59.251547+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/6CAF4ZWYNBT2VA4M3ITC2ROQ3J","json":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J.json","graph_json":"https://pith.science/api/pith-number/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/graph.json","events_json":"https://pith.science/api/pith-number/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/events.json","paper":"https://pith.science/paper/6CAF4ZWY"},"agent_actions":{"view_html":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J","download_json":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J.json","view_paper":"https://pith.science/paper/6CAF4ZWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04228&json=true","fetch_graph":"https://pith.science/api/pith-number/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/graph.json","fetch_events":"https://pith.science/api/pith-number/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/action/storage_attestation","attest_author":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/action/author_attestation","sign_citation":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/action/citation_signature","submit_replication":"https://pith.science/pith/6CAF4ZWYNBT2VA4M3ITC2ROQ3J/action/replication_record"}},"created_at":"2026-06-04T01:08:59.251547+00:00","updated_at":"2026-06-04T01:08:59.251547+00:00"}