{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LXCR2BOCI3ATVZTPUCRSAR2BX7","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":"944e3f19825e32d055d679b19d34fd023b56b1930a419d658f293a11b1c5b10f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-04T15:57:28Z","title_canon_sha256":"145e8a0c1da93162c61ed4d48aaa45e0e0fee091b19b9ecbf9e3d2d77fe04679"},"schema_version":"1.0","source":{"id":"2304.01904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.01904","created_at":"2026-07-05T07:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"2304.01904v2","created_at":"2026-07-05T07:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01904","created_at":"2026-07-05T07:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"LXCR2BOCI3AT","created_at":"2026-07-05T07:40:52Z"},{"alias_kind":"pith_short_16","alias_value":"LXCR2BOCI3ATVZTP","created_at":"2026-07-05T07:40:52Z"},{"alias_kind":"pith_short_8","alias_value":"LXCR2BOC","created_at":"2026-07-05T07:40:52Z"}],"graph_snapshots":[{"event_id":"sha256:a7ecb82a713db6c54a25e16d29c1b2e5164266a91b61697094a565957e064531","target":"graph","created_at":"2026-07-05T07:40:52Z","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/2304.01904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate deductions from the initial context and lead to incorrect final predictions. Here we introduce REFINER, a framework for finetuning LMs to explicitly generate intermediate reasoning steps while interacting with a critic model that provides automated feedback on the reasoning. Specifically, the critic provides structured feedback that the reasoning LM uses to iterati","authors_text":"Antoine Bosselut, Beatriz Borges, Boi Faltings, Debjit Paul, Maxime Peyrard, Mete Ismayilzada, Robert West","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-04T15:57:28Z","title":"REFINER: Reasoning Feedback on Intermediate Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01904","kind":"arxiv","version":2},"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":"sha256:79d8cb6334c1b90259955cd94b6941886f4c52c031341dbf949f6380246cdbbc","target":"record","created_at":"2026-07-05T07:40:52Z","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":"944e3f19825e32d055d679b19d34fd023b56b1930a419d658f293a11b1c5b10f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-04T15:57:28Z","title_canon_sha256":"145e8a0c1da93162c61ed4d48aaa45e0e0fee091b19b9ecbf9e3d2d77fe04679"},"schema_version":"1.0","source":{"id":"2304.01904","kind":"arxiv","version":2}},"canonical_sha256":"5dc51d05c246c13ae66fa0a3204741bfd88ec5a865d5f1581372fbdb7741962b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dc51d05c246c13ae66fa0a3204741bfd88ec5a865d5f1581372fbdb7741962b","first_computed_at":"2026-07-05T07:40:52.605653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:52.605653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfC7Ha/mZMjmOSDPF8eekc7C7xmULxGrtxFjxLhXUbDvWw9hHxGGFtWmgqA7mPLFdJ/B2KiF/2D71JGgHV+SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:52.606063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.01904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79d8cb6334c1b90259955cd94b6941886f4c52c031341dbf949f6380246cdbbc","sha256:a7ecb82a713db6c54a25e16d29c1b2e5164266a91b61697094a565957e064531"],"state_sha256":"35121f8f31fbcf5221787a6f88ca5f5438102a406aeb0a5b7a6e9a9a9d66f0c2"}