{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7QOTMHILZLJCU3XWQE23VBVWC6","short_pith_number":"pith:7QOTMHIL","canonical_record":{"source":{"id":"2404.08828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T21:59:42Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"d4795b0598f3adb3d69c402d6dfc05851a3856d21ab93be0e7384d7e35d14cc0","abstract_canon_sha256":"08cc6431df3bef3e5c071a26c1e373ecb9576d8fc3f67f8d2c1578e30ed864d1"},"schema_version":"1.0"},"canonical_sha256":"fc1d361d0bcad22a6ef68135ba86b6178af01c2803bb498ea8eb8e57bafeb2ca","source":{"kind":"arxiv","id":"2404.08828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08828","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08828v1","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08828","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"7QOTMHILZLJC","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"7QOTMHILZLJCU3XW","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"7QOTMHIL","created_at":"2026-07-05T08:07:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7QOTMHILZLJCU3XWQE23VBVWC6","target":"record","payload":{"canonical_record":{"source":{"id":"2404.08828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T21:59:42Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"d4795b0598f3adb3d69c402d6dfc05851a3856d21ab93be0e7384d7e35d14cc0","abstract_canon_sha256":"08cc6431df3bef3e5c071a26c1e373ecb9576d8fc3f67f8d2c1578e30ed864d1"},"schema_version":"1.0"},"canonical_sha256":"fc1d361d0bcad22a6ef68135ba86b6178af01c2803bb498ea8eb8e57bafeb2ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:40.793980Z","signature_b64":"k5FzVwTHiPwzTnQi7rKvE8WZInM37pLjBQH2Yx1ZSJ3qNGprI5DZk1c/A8ETLvrpYpRFj9ehaShdYNz9E9RIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc1d361d0bcad22a6ef68135ba86b6178af01c2803bb498ea8eb8e57bafeb2ca","last_reissued_at":"2026-07-05T08:07:40.793542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:40.793542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.08828","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":"2026-07-05T08:07:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPZrkhMv9wY27smYDZATEoKG8TyR5ccfmDagZCbqTgp9yi8OyQBiSbHEIRqa0ESzyoLIuFzZx/VxmLwkQSXvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:07:12.300383Z"},"content_sha256":"09d761ddf4267f3b1f93817fb6d3e49b70a03681fda6142a9e43a65e4b8e01f2","schema_version":"1.0","event_id":"sha256:09d761ddf4267f3b1f93817fb6d3e49b70a03681fda6142a9e43a65e4b8e01f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7QOTMHILZLJCU3XWQE23VBVWC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hindsight PRIORs for Reward Learning from Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Katherine Metcalf, Mudit Verma","submitted_at":"2024-04-12T21:59:42Z","abstract_excerpt":"Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem inherent in determining which parts of a behavior most contributed to a preference, which result in data intensive approaches and subpar reward functions. We address such limitations by introducing a credit assignment strategy (Hindsight PRIOR) that uses a world model to approximate state importance within a trajectory and then guides rewards to be proportion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08828","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/2404.08828/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":"2026-07-05T08:07:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8b7tpYmyhfqI02Dc6JPJ4e2L0lLrlcmfAnG8trxKZikjfwVMJLtKJCKaKtvo6yCchyoO2Ou9qi/UxCVvqrQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:07:12.300932Z"},"content_sha256":"7800994e9c6835f743948f0bbc6a0379eebd7268f826ffc7cc24fd0c16802f5f","schema_version":"1.0","event_id":"sha256:7800994e9c6835f743948f0bbc6a0379eebd7268f826ffc7cc24fd0c16802f5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QOTMHILZLJCU3XWQE23VBVWC6/bundle.json","state_url":"https://pith.science/pith/7QOTMHILZLJCU3XWQE23VBVWC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QOTMHILZLJCU3XWQE23VBVWC6/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":"2026-08-16T23:07:12Z","links":{"resolver":"https://pith.science/pith/7QOTMHILZLJCU3XWQE23VBVWC6","bundle":"https://pith.science/pith/7QOTMHILZLJCU3XWQE23VBVWC6/bundle.json","state":"https://pith.science/pith/7QOTMHILZLJCU3XWQE23VBVWC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QOTMHILZLJCU3XWQE23VBVWC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7QOTMHILZLJCU3XWQE23VBVWC6","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":"08cc6431df3bef3e5c071a26c1e373ecb9576d8fc3f67f8d2c1578e30ed864d1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T21:59:42Z","title_canon_sha256":"d4795b0598f3adb3d69c402d6dfc05851a3856d21ab93be0e7384d7e35d14cc0"},"schema_version":"1.0","source":{"id":"2404.08828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08828","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08828v1","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08828","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"7QOTMHILZLJC","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"7QOTMHILZLJCU3XW","created_at":"2026-07-05T08:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"7QOTMHIL","created_at":"2026-07-05T08:07:40Z"}],"graph_snapshots":[{"event_id":"sha256:7800994e9c6835f743948f0bbc6a0379eebd7268f826ffc7cc24fd0c16802f5f","target":"graph","created_at":"2026-07-05T08:07:40Z","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/2404.08828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem inherent in determining which parts of a behavior most contributed to a preference, which result in data intensive approaches and subpar reward functions. We address such limitations by introducing a credit assignment strategy (Hindsight PRIOR) that uses a world model to approximate state importance within a trajectory and then guides rewards to be proportion","authors_text":"Katherine Metcalf, Mudit Verma","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T21:59:42Z","title":"Hindsight PRIORs for Reward Learning from Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08828","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":"sha256:09d761ddf4267f3b1f93817fb6d3e49b70a03681fda6142a9e43a65e4b8e01f2","target":"record","created_at":"2026-07-05T08:07:40Z","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":"08cc6431df3bef3e5c071a26c1e373ecb9576d8fc3f67f8d2c1578e30ed864d1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T21:59:42Z","title_canon_sha256":"d4795b0598f3adb3d69c402d6dfc05851a3856d21ab93be0e7384d7e35d14cc0"},"schema_version":"1.0","source":{"id":"2404.08828","kind":"arxiv","version":1}},"canonical_sha256":"fc1d361d0bcad22a6ef68135ba86b6178af01c2803bb498ea8eb8e57bafeb2ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc1d361d0bcad22a6ef68135ba86b6178af01c2803bb498ea8eb8e57bafeb2ca","first_computed_at":"2026-07-05T08:07:40.793542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:40.793542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k5FzVwTHiPwzTnQi7rKvE8WZInM37pLjBQH2Yx1ZSJ3qNGprI5DZk1c/A8ETLvrpYpRFj9ehaShdYNz9E9RIDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:40.793980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09d761ddf4267f3b1f93817fb6d3e49b70a03681fda6142a9e43a65e4b8e01f2","sha256:7800994e9c6835f743948f0bbc6a0379eebd7268f826ffc7cc24fd0c16802f5f"],"state_sha256":"6a5b85eb57ecc845859fabb0bce65c3a22978969e35d6e1720782785498f36e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdXbnoO1/61TffhhzHe1ZZ+U794BtkskH9x4FlPIRI34Ha0b+YK6YVCtJT/O4YAG8kEFeHD10peJh+ZF7jixBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:07:12.306134Z","bundle_sha256":"408625322e295c974503df6a93bb582e3f111fbe50ee545ec4987a04c030c588"}}