{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C6JD36EZWRFVIB3OW3C2JYRPHP","short_pith_number":"pith:C6JD36EZ","schema_version":"1.0","canonical_sha256":"17923df899b44b54076eb6c5a4e22f3bc2f22ef03f31c61b60a0ef041a9a249a","source":{"kind":"arxiv","id":"2607.09195","version":1},"attestation_state":"computed","paper":{"title":"Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.AI","authors_text":"Izumi Takahara, Teruyasu Mizoguchi","submitted_at":"2026-07-10T08:39:30Z","abstract_excerpt":"Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are buried in unstructured logs, and no mechanism lets the agent or the human researcher audit that process. Here we propose the Hypothesis Evolution Protocol ("},"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":"2607.09195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T08:39:30Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"0e5343925247eee57c72ad117e14cdb7ac61df8faa4050a47f3c723285f48e4d","abstract_canon_sha256":"448be2aa2ecc35eadc3cefd294574dffcd4540f848265fe4daf091c22482be55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:18:50.404155Z","signature_b64":"P8OnfqcRLXv+jDKz2cX/g223KzvXUfKVYQ4Kz7NDcUK7nTKQlPZay2iq03XbzYhaiQXwWi4ffSHbbLyv+lIJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17923df899b44b54076eb6c5a4e22f3bc2f22ef03f31c61b60a0ef041a9a249a","last_reissued_at":"2026-07-13T01:18:50.402726Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:18:50.402726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.AI","authors_text":"Izumi Takahara, Teruyasu Mizoguchi","submitted_at":"2026-07-10T08:39:30Z","abstract_excerpt":"Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are buried in unstructured logs, and no mechanism lets the agent or the human researcher audit that process. Here we propose the Hypothesis Evolution Protocol ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09195","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/2607.09195/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":"2607.09195","created_at":"2026-07-13T01:18:50.403606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09195v1","created_at":"2026-07-13T01:18:50.403606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09195","created_at":"2026-07-13T01:18:50.403606+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6JD36EZWRFV","created_at":"2026-07-13T01:18:50.403606+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6JD36EZWRFVIB3O","created_at":"2026-07-13T01:18:50.403606+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6JD36EZ","created_at":"2026-07-13T01:18:50.403606+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/C6JD36EZWRFVIB3OW3C2JYRPHP","json":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP.json","graph_json":"https://pith.science/api/pith-number/C6JD36EZWRFVIB3OW3C2JYRPHP/graph.json","events_json":"https://pith.science/api/pith-number/C6JD36EZWRFVIB3OW3C2JYRPHP/events.json","paper":"https://pith.science/paper/C6JD36EZ"},"agent_actions":{"view_html":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP","download_json":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP.json","view_paper":"https://pith.science/paper/C6JD36EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09195&json=true","fetch_graph":"https://pith.science/api/pith-number/C6JD36EZWRFVIB3OW3C2JYRPHP/graph.json","fetch_events":"https://pith.science/api/pith-number/C6JD36EZWRFVIB3OW3C2JYRPHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP/action/storage_attestation","attest_author":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP/action/author_attestation","sign_citation":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP/action/citation_signature","submit_replication":"https://pith.science/pith/C6JD36EZWRFVIB3OW3C2JYRPHP/action/replication_record"}},"created_at":"2026-07-13T01:18:50.403606+00:00","updated_at":"2026-07-13T01:18:50.403606+00:00"}