{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBDBYXI4GSD2FRVA6C3GIKLVAA","short_pith_number":"pith:HBDBYXI4","schema_version":"1.0","canonical_sha256":"38461c5d1c3487a2c6a0f0b6642975001aae0fecef4059f8b4d2f08ce9848aa3","source":{"kind":"arxiv","id":"2607.21856","version":1},"attestation_state":"computed","paper":{"title":"LeAct: Learning to Reason from Expert Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Chengshuai Shi, Chi Jin, Karthik Narasimhan, Raj Ghugare, Ziran Yang","submitted_at":"2026-07-23T22:50:23Z","abstract_excerpt":"Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision lies in expert systems (e.g., game engines, classical planners, theorem provers), which routinely produce near-optimal actions across diverse domains. But these experts are silent: they commit to an action without writing down the chain of thought (CoT) behind it. Recovering that CoT as natural-language reasoning would distill expert knowledge into a student that generalizes beyond the demonstrated actions. We treat i"},"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":"2607.21856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T22:50:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"17b0b860e1fb697eb78cf921189c9335ba3a1769b6c319fb34846a0963fb1757","abstract_canon_sha256":"b75fc04f3382c0078205ca7f29fb25ba545cefaaafc67a92914b3d366208390d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:24.566183Z","signature_b64":"J5JnyMe8ztsHi8w1FD+USJ5XtraGN8D4ggg+lBxmSNe7tv7O9ItDLdOvtJ8MH5bSDLgYLsZf2cmgxrJD7WUcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38461c5d1c3487a2c6a0f0b6642975001aae0fecef4059f8b4d2f08ce9848aa3","last_reissued_at":"2026-07-27T00:20:24.565326Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:24.565326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeAct: Learning to Reason from Expert Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Chengshuai Shi, Chi Jin, Karthik Narasimhan, Raj Ghugare, Ziran Yang","submitted_at":"2026-07-23T22:50:23Z","abstract_excerpt":"Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision lies in expert systems (e.g., game engines, classical planners, theorem provers), which routinely produce near-optimal actions across diverse domains. But these experts are silent: they commit to an action without writing down the chain of thought (CoT) behind it. Recovering that CoT as natural-language reasoning would distill expert knowledge into a student that generalizes beyond the demonstrated actions. We treat i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21856","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/2607.21856/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":"2607.21856","created_at":"2026-07-27T00:20:24.565769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21856v1","created_at":"2026-07-27T00:20:24.565769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21856","created_at":"2026-07-27T00:20:24.565769+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBDBYXI4GSD2","created_at":"2026-07-27T00:20:24.565769+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBDBYXI4GSD2FRVA","created_at":"2026-07-27T00:20:24.565769+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBDBYXI4","created_at":"2026-07-27T00:20:24.565769+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/HBDBYXI4GSD2FRVA6C3GIKLVAA","json":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA.json","graph_json":"https://pith.science/api/pith-number/HBDBYXI4GSD2FRVA6C3GIKLVAA/graph.json","events_json":"https://pith.science/api/pith-number/HBDBYXI4GSD2FRVA6C3GIKLVAA/events.json","paper":"https://pith.science/paper/HBDBYXI4"},"agent_actions":{"view_html":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA","download_json":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA.json","view_paper":"https://pith.science/paper/HBDBYXI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21856&json=true","fetch_graph":"https://pith.science/api/pith-number/HBDBYXI4GSD2FRVA6C3GIKLVAA/graph.json","fetch_events":"https://pith.science/api/pith-number/HBDBYXI4GSD2FRVA6C3GIKLVAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA/action/storage_attestation","attest_author":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA/action/author_attestation","sign_citation":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA/action/citation_signature","submit_replication":"https://pith.science/pith/HBDBYXI4GSD2FRVA6C3GIKLVAA/action/replication_record"}},"created_at":"2026-07-27T00:20:24.565769+00:00","updated_at":"2026-07-27T00:20:24.565769+00:00"}