{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BGFA4ICRWHNGMAKEP72GIFR72D","short_pith_number":"pith:BGFA4ICR","canonical_record":{"source":{"id":"2303.16755","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-28T17:04:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"67cc2efdb93ee5fb6290af2923ea91c84cf4ff1af77b5f84f555cbe11531348c","abstract_canon_sha256":"0082c50fab6b6a9c70fd7d2110c5e2d2f5202514ef8aecfb17d687a5856b9c09"},"schema_version":"1.0"},"canonical_sha256":"098a0e2051b1da6601447ff464163fd0e66114336f87e9e455fea53803ef473d","source":{"kind":"arxiv","id":"2303.16755","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16755","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16755v3","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16755","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"BGFA4ICRWHNG","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"BGFA4ICRWHNGMAKE","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"BGFA4ICR","created_at":"2026-07-05T07:48:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BGFA4ICRWHNGMAKEP72GIFR72D","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16755","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-28T17:04:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"67cc2efdb93ee5fb6290af2923ea91c84cf4ff1af77b5f84f555cbe11531348c","abstract_canon_sha256":"0082c50fab6b6a9c70fd7d2110c5e2d2f5202514ef8aecfb17d687a5856b9c09"},"schema_version":"1.0"},"canonical_sha256":"098a0e2051b1da6601447ff464163fd0e66114336f87e9e455fea53803ef473d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:16.053780Z","signature_b64":"2Egg9QqRs+TceQuTfx8bYo23AhP6lKeufvC0LdDarQxLLPFKEZEEmMPGPPV3uHPQboXXRRDn6ekqEz3uMTTNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098a0e2051b1da6601447ff464163fd0e66114336f87e9e455fea53803ef473d","last_reissued_at":"2026-07-05T07:48:16.053285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:16.053285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16755","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2Hlb+T73nPA3IOTqJzUuiOvAlfJz0dq6DVu4FX/YsDa7zVoZAxHdDUTqOgxY2kXTlo9HHn/e4ZLYP4xAOw4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:37:16.586574Z"},"content_sha256":"72d53a2030ef49d0fb3d0fced573087f3684670327962ac0810bea98ad01150b","schema_version":"1.0","event_id":"sha256:72d53a2030ef49d0fb3d0fced573087f3684670327962ac0810bea98ad01150b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BGFA4ICRWHNGMAKEP72GIFR72D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Language Models with Language Feedback at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Angelica Chen, Ethan Perez, J\\'er\\'emy Scheurer, Jon Ander Campos, Jun Shern Chan, Kyunghyun Cho, Tomasz Korbak","submitted_at":"2023-03-28T17:04:15Z","abstract_excerpt":"Pretrained language models often generate outputs that are not in line with human preferences, such as harmful text or factually incorrect summaries. Recent work approaches the above issues by learning from a simple form of human feedback: comparisons between pairs of model-generated outputs. However, comparison feedback only conveys limited information about human preferences. In this paper, we introduce Imitation learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16755","kind":"arxiv","version":3},"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/2303.16755/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":"2026-07-05T07:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYzOYr2brSstTLs+BdxyTwcgAxsKx205TfFtR8rVsdzXMPj35Ie67v+QNXn6SWcBZcrqd3ekSySCVIFqXWzJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:37:16.587089Z"},"content_sha256":"5f9803bf82572bc5d95df00a6c9622648a4b6471bf0867e478c9ec72c4a5c936","schema_version":"1.0","event_id":"sha256:5f9803bf82572bc5d95df00a6c9622648a4b6471bf0867e478c9ec72c4a5c936"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGFA4ICRWHNGMAKEP72GIFR72D/bundle.json","state_url":"https://pith.science/pith/BGFA4ICRWHNGMAKEP72GIFR72D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGFA4ICRWHNGMAKEP72GIFR72D/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":"2026-08-08T13:37:16Z","links":{"resolver":"https://pith.science/pith/BGFA4ICRWHNGMAKEP72GIFR72D","bundle":"https://pith.science/pith/BGFA4ICRWHNGMAKEP72GIFR72D/bundle.json","state":"https://pith.science/pith/BGFA4ICRWHNGMAKEP72GIFR72D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGFA4ICRWHNGMAKEP72GIFR72D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BGFA4ICRWHNGMAKEP72GIFR72D","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":"0082c50fab6b6a9c70fd7d2110c5e2d2f5202514ef8aecfb17d687a5856b9c09","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-28T17:04:15Z","title_canon_sha256":"67cc2efdb93ee5fb6290af2923ea91c84cf4ff1af77b5f84f555cbe11531348c"},"schema_version":"1.0","source":{"id":"2303.16755","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16755","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16755v3","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16755","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"BGFA4ICRWHNG","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"BGFA4ICRWHNGMAKE","created_at":"2026-07-05T07:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"BGFA4ICR","created_at":"2026-07-05T07:48:16Z"}],"graph_snapshots":[{"event_id":"sha256:5f9803bf82572bc5d95df00a6c9622648a4b6471bf0867e478c9ec72c4a5c936","target":"graph","created_at":"2026-07-05T07:48:16Z","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/2303.16755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models often generate outputs that are not in line with human preferences, such as harmful text or factually incorrect summaries. Recent work approaches the above issues by learning from a simple form of human feedback: comparisons between pairs of model-generated outputs. However, comparison feedback only conveys limited information about human preferences. In this paper, we introduce Imitation learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning","authors_text":"Angelica Chen, Ethan Perez, J\\'er\\'emy Scheurer, Jon Ander Campos, Jun Shern Chan, Kyunghyun Cho, Tomasz Korbak","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-28T17:04:15Z","title":"Training Language Models with Language Feedback at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16755","kind":"arxiv","version":3},"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":"sha256:72d53a2030ef49d0fb3d0fced573087f3684670327962ac0810bea98ad01150b","target":"record","created_at":"2026-07-05T07:48:16Z","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":"0082c50fab6b6a9c70fd7d2110c5e2d2f5202514ef8aecfb17d687a5856b9c09","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-28T17:04:15Z","title_canon_sha256":"67cc2efdb93ee5fb6290af2923ea91c84cf4ff1af77b5f84f555cbe11531348c"},"schema_version":"1.0","source":{"id":"2303.16755","kind":"arxiv","version":3}},"canonical_sha256":"098a0e2051b1da6601447ff464163fd0e66114336f87e9e455fea53803ef473d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"098a0e2051b1da6601447ff464163fd0e66114336f87e9e455fea53803ef473d","first_computed_at":"2026-07-05T07:48:16.053285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:16.053285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Egg9QqRs+TceQuTfx8bYo23AhP6lKeufvC0LdDarQxLLPFKEZEEmMPGPPV3uHPQboXXRRDn6ekqEz3uMTTNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:16.053780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16755","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d53a2030ef49d0fb3d0fced573087f3684670327962ac0810bea98ad01150b","sha256:5f9803bf82572bc5d95df00a6c9622648a4b6471bf0867e478c9ec72c4a5c936"],"state_sha256":"a86caf5ab1530e631b8864616d14d27e25d188ada320501b757620c27f9c1ae5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMUTRUDCaLLVMI9hL+7biC7gqpwDidJbRTDg6fntw2baknSMe40SyoU4O6uw65tyoK6aT1HStlcw0+5fPzN1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:37:16.591475Z","bundle_sha256":"c944e9e8316a9bc50eced32e6b4a39eb9b2e33e6646b10de1ff1b8f1ab4128b8"}}