{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IYQGHBUF7YTZNHSNKSIXFS32NB","short_pith_number":"pith:IYQGHBUF","canonical_record":{"source":{"id":"2302.02676","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T10:28:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7ab42bb991ad46ff93723cfe4fb6832fc0c1dd5108d87e43eae55b0afdc61781","abstract_canon_sha256":"40b167e8d456da121b240c068b29e7e900df2cc3d46b6246d57ecbd48329d9df"},"schema_version":"1.0"},"canonical_sha256":"4620638685fe27969e4d549172cb7a684f11beff1cdc6e58d2d48a8a1732188f","source":{"kind":"arxiv","id":"2302.02676","version":8},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02676","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02676v8","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02676","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"IYQGHBUF7YTZ","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"IYQGHBUF7YTZNHSN","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"IYQGHBUF","created_at":"2026-07-05T07:01:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IYQGHBUF7YTZNHSNKSIXFS32NB","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02676","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T10:28:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7ab42bb991ad46ff93723cfe4fb6832fc0c1dd5108d87e43eae55b0afdc61781","abstract_canon_sha256":"40b167e8d456da121b240c068b29e7e900df2cc3d46b6246d57ecbd48329d9df"},"schema_version":"1.0"},"canonical_sha256":"4620638685fe27969e4d549172cb7a684f11beff1cdc6e58d2d48a8a1732188f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:58.610207Z","signature_b64":"XgQYS7kn+bJtlCQi6hiFgFrGCj1W/g1VE4UgmXAsyK8m90tdDCTfFp5cXrfHHLKPOxGiTiw8x/LTSBfgdrqEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4620638685fe27969e4d549172cb7a684f11beff1cdc6e58d2d48a8a1732188f","last_reissued_at":"2026-07-05T07:01:58.609705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:58.609705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02676","source_version":8,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"12/1PoCjWtljAq34STHNfs40MToMRe3eCTliYouQiD9YwDV8y4/Gs0JcR6mGj0AAmiDE5tV4AbjX8aqTjVyVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:48:49.716071Z"},"content_sha256":"9341579086daa3e9581682ed11e663890e4be7d368ca117069c4bcb08bf7242c","schema_version":"1.0","event_id":"sha256:9341579086daa3e9581682ed11e663890e4be7d368ca117069c4bcb08bf7242c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IYQGHBUF7YTZNHSNKSIXFS32NB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chain of Hindsight Aligns Language Models with Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Carmelo Sferrazza, Hao Liu, Pieter Abbeel","submitted_at":"2023-02-06T10:28:16Z","abstract_excerpt":"Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow instructions. Nonetheless, these methods are either founded on hand-picked model generations that are favored by human annotators, rendering them inefficient in terms of data utilization and challenging to apply in general, or they depend on reinforcement learning, which often suffers from imperfect reward functions and relies on extremely challenging optimizations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02676","kind":"arxiv","version":8},"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/2302.02676/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":"2026-07-05T07:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEPLDcPiPM9Tcz4zsqfShHy/V77IaDSNoR9ThoW3k3RYMjeeIpDV6YRvtjxNny0dnrZBA6Ul26DQb1dLn3QCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:48:49.716988Z"},"content_sha256":"459243a9d6459725341656714e7565665a09380a355f370b190f19ae5fb08324","schema_version":"1.0","event_id":"sha256:459243a9d6459725341656714e7565665a09380a355f370b190f19ae5fb08324"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/bundle.json","state_url":"https://pith.science/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/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":"2026-08-04T11:48:49Z","links":{"resolver":"https://pith.science/pith/IYQGHBUF7YTZNHSNKSIXFS32NB","bundle":"https://pith.science/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/bundle.json","state":"https://pith.science/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYQGHBUF7YTZNHSNKSIXFS32NB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IYQGHBUF7YTZNHSNKSIXFS32NB","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":"40b167e8d456da121b240c068b29e7e900df2cc3d46b6246d57ecbd48329d9df","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T10:28:16Z","title_canon_sha256":"7ab42bb991ad46ff93723cfe4fb6832fc0c1dd5108d87e43eae55b0afdc61781"},"schema_version":"1.0","source":{"id":"2302.02676","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02676","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02676v8","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02676","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"IYQGHBUF7YTZ","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"IYQGHBUF7YTZNHSN","created_at":"2026-07-05T07:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"IYQGHBUF","created_at":"2026-07-05T07:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:459243a9d6459725341656714e7565665a09380a355f370b190f19ae5fb08324","target":"graph","created_at":"2026-07-05T07:01:58Z","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/2302.02676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow instructions. Nonetheless, these methods are either founded on hand-picked model generations that are favored by human annotators, rendering them inefficient in terms of data utilization and challenging to apply in general, or they depend on reinforcement learning, which often suffers from imperfect reward functions and relies on extremely challenging optimizations","authors_text":"Carmelo Sferrazza, Hao Liu, Pieter Abbeel","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T10:28:16Z","title":"Chain of Hindsight Aligns Language Models with Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02676","kind":"arxiv","version":8},"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":"sha256:9341579086daa3e9581682ed11e663890e4be7d368ca117069c4bcb08bf7242c","target":"record","created_at":"2026-07-05T07:01:58Z","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":"40b167e8d456da121b240c068b29e7e900df2cc3d46b6246d57ecbd48329d9df","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T10:28:16Z","title_canon_sha256":"7ab42bb991ad46ff93723cfe4fb6832fc0c1dd5108d87e43eae55b0afdc61781"},"schema_version":"1.0","source":{"id":"2302.02676","kind":"arxiv","version":8}},"canonical_sha256":"4620638685fe27969e4d549172cb7a684f11beff1cdc6e58d2d48a8a1732188f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4620638685fe27969e4d549172cb7a684f11beff1cdc6e58d2d48a8a1732188f","first_computed_at":"2026-07-05T07:01:58.609705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:58.609705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XgQYS7kn+bJtlCQi6hiFgFrGCj1W/g1VE4UgmXAsyK8m90tdDCTfFp5cXrfHHLKPOxGiTiw8x/LTSBfgdrqEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:58.610207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02676","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9341579086daa3e9581682ed11e663890e4be7d368ca117069c4bcb08bf7242c","sha256:459243a9d6459725341656714e7565665a09380a355f370b190f19ae5fb08324"],"state_sha256":"ee611ed941855a7dbaabe9ce74000029309f5f2789e729a664350eca0f29d8a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3ILB3z9OtTIJJBmQATseiMHh1sJdVWOnwfNDufMRv8nWHPXLPP1I3lQVCeGkjdSX8wM707OjVfB0qKsiO6HAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:48:49.722613Z","bundle_sha256":"73f57968bdabbb04d6fbb80f1029a96fc41890ff7c3e39d40d5a964b30c2563d"}}