{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KASNF2BD2GEL4JKWKQXMPEP4WK","short_pith_number":"pith:KASNF2BD","canonical_record":{"source":{"id":"2506.15651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T17:29:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"900998390ae6cae888b3c4c5af72fd121172d2d1e3c79a68a9afc6b5b61628fd","abstract_canon_sha256":"62deaa634e36128c27600bda6451ada8380e828d54309c5b5f077b40fbe63afb"},"schema_version":"1.0"},"canonical_sha256":"5024d2e823d188be2556542ec791fcb2a076296eb1cf295c115153babe7fbded","source":{"kind":"arxiv","id":"2506.15651","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15651","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15651v1","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15651","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"KASNF2BD2GEL","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"KASNF2BD2GEL4JKW","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"KASNF2BD","created_at":"2026-07-05T11:23:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KASNF2BD2GEL4JKWKQXMPEP4WK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T17:29:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"900998390ae6cae888b3c4c5af72fd121172d2d1e3c79a68a9afc6b5b61628fd","abstract_canon_sha256":"62deaa634e36128c27600bda6451ada8380e828d54309c5b5f077b40fbe63afb"},"schema_version":"1.0"},"canonical_sha256":"5024d2e823d188be2556542ec791fcb2a076296eb1cf295c115153babe7fbded","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:47.796441Z","signature_b64":"YTam8Xp6VWK7n2lWTd+oceRi123bn4d4KbBZ9x1w7BSueJzN26BmwFGI4vygz6E6DlklDUDs6i76klBy5+VHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5024d2e823d188be2556542ec791fcb2a076296eb1cf295c115153babe7fbded","last_reissued_at":"2026-07-05T11:23:47.795893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:47.795893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15651","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iz61ZBR9MsgfKVmKKdIOJCapUI5lJUIwaBv8TVVzHbWiUp9IiJEo6s0dBjNOjvr2qnqeOAqIyUlI2hodidrMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:09:51.523041Z"},"content_sha256":"7fc500f8b49b037a58f634807ef01fd7a5db3d3b7f378bae13aece422bf2b957","schema_version":"1.0","event_id":"sha256:7fc500f8b49b037a58f634807ef01fd7a5db3d3b7f378bae13aece422bf2b957"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KASNF2BD2GEL4JKWKQXMPEP4WK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenyan Xiong, Tevin Wang","submitted_at":"2025-06-18T17:29:19Z","abstract_excerpt":"Rule-based rewards offer a promising strategy for improving reinforcement learning from human feedback (RLHF), but current approaches often rely on manual rule engineering. We present AutoRule, a fully automated method for extracting rules from preference feedback and formulating them into rule-based rewards. AutoRule extraction operates in three stages: it leverages a reasoning model to interpret user preferences, identifies candidate rules from the reasoning chain of these interpretations, and synthesizes them into a unified rule set. Leveraging the finalized rule set, we employ language-mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15651","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/2506.15651/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlgafpowE2bSTuTJSDQZCwwnxFBgw+iipQRn2ep1zmooXJcplA8jI6pnKPrrLeSmma87ynfPqNvNYPjXX/05Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:09:51.523971Z"},"content_sha256":"e707eb37f12802b91ddd1707fe911dce52ed15016402f2a4459c239c69eba09a","schema_version":"1.0","event_id":"sha256:e707eb37f12802b91ddd1707fe911dce52ed15016402f2a4459c239c69eba09a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/bundle.json","state_url":"https://pith.science/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:09:51Z","links":{"resolver":"https://pith.science/pith/KASNF2BD2GEL4JKWKQXMPEP4WK","bundle":"https://pith.science/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/bundle.json","state":"https://pith.science/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KASNF2BD2GEL4JKWKQXMPEP4WK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KASNF2BD2GEL4JKWKQXMPEP4WK","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":"62deaa634e36128c27600bda6451ada8380e828d54309c5b5f077b40fbe63afb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T17:29:19Z","title_canon_sha256":"900998390ae6cae888b3c4c5af72fd121172d2d1e3c79a68a9afc6b5b61628fd"},"schema_version":"1.0","source":{"id":"2506.15651","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15651","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15651v1","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15651","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"KASNF2BD2GEL","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"KASNF2BD2GEL4JKW","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"KASNF2BD","created_at":"2026-07-05T11:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:e707eb37f12802b91ddd1707fe911dce52ed15016402f2a4459c239c69eba09a","target":"graph","created_at":"2026-07-05T11:23:47Z","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/2506.15651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rule-based rewards offer a promising strategy for improving reinforcement learning from human feedback (RLHF), but current approaches often rely on manual rule engineering. We present AutoRule, a fully automated method for extracting rules from preference feedback and formulating them into rule-based rewards. AutoRule extraction operates in three stages: it leverages a reasoning model to interpret user preferences, identifies candidate rules from the reasoning chain of these interpretations, and synthesizes them into a unified rule set. Leveraging the finalized rule set, we employ language-mod","authors_text":"Chenyan Xiong, Tevin Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T17:29:19Z","title":"AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15651","kind":"arxiv","version":1},"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":"sha256:7fc500f8b49b037a58f634807ef01fd7a5db3d3b7f378bae13aece422bf2b957","target":"record","created_at":"2026-07-05T11:23:47Z","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":"62deaa634e36128c27600bda6451ada8380e828d54309c5b5f077b40fbe63afb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T17:29:19Z","title_canon_sha256":"900998390ae6cae888b3c4c5af72fd121172d2d1e3c79a68a9afc6b5b61628fd"},"schema_version":"1.0","source":{"id":"2506.15651","kind":"arxiv","version":1}},"canonical_sha256":"5024d2e823d188be2556542ec791fcb2a076296eb1cf295c115153babe7fbded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5024d2e823d188be2556542ec791fcb2a076296eb1cf295c115153babe7fbded","first_computed_at":"2026-07-05T11:23:47.795893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:47.795893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YTam8Xp6VWK7n2lWTd+oceRi123bn4d4KbBZ9x1w7BSueJzN26BmwFGI4vygz6E6DlklDUDs6i76klBy5+VHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:47.796441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15651","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fc500f8b49b037a58f634807ef01fd7a5db3d3b7f378bae13aece422bf2b957","sha256:e707eb37f12802b91ddd1707fe911dce52ed15016402f2a4459c239c69eba09a"],"state_sha256":"427a874e16bd4c5eb93dc663d7f9ac2b455382be05330fa3e49a4840e95c55dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FMZVUv4ksQV9OoA2OLAruVEVQD2MC1fW7TjH0aT/xNz2Enm2AOB+l9eWh2x6AGecLrZZxZ4+1Z3PDE8ADAwvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:09:51.530866Z","bundle_sha256":"d9193634bc946e5dfadbe75a3850d411f2247e65d411299763e1b446cc59ae40"}}