{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NNDJBHYX2NAPF4JNXLXA2UNKM2","short_pith_number":"pith:NNDJBHYX","canonical_record":{"source":{"id":"2402.07876","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T18:41:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6fad1ad812949a1b6b11081376e986472efb510eb27b1f879365d35c083d146b","abstract_canon_sha256":"776f0d0e8712177ae9b04011e39dc56fe9b385be1038bc99871916f739e4550d"},"schema_version":"1.0"},"canonical_sha256":"6b46909f17d340f2f12dbaee0d51aa66a8b21426e25cd9adb84a04465edec5b6","source":{"kind":"arxiv","id":"2402.07876","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07876","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07876v6","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07876","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"NNDJBHYX2NAP","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"NNDJBHYX2NAPF4JN","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"NNDJBHYX","created_at":"2026-07-05T09:18:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NNDJBHYX2NAPF4JNXLXA2UNKM2","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07876","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T18:41:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6fad1ad812949a1b6b11081376e986472efb510eb27b1f879365d35c083d146b","abstract_canon_sha256":"776f0d0e8712177ae9b04011e39dc56fe9b385be1038bc99871916f739e4550d"},"schema_version":"1.0"},"canonical_sha256":"6b46909f17d340f2f12dbaee0d51aa66a8b21426e25cd9adb84a04465edec5b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:22.918370Z","signature_b64":"tW0PXY5avWYhbWk9yVVT6XDjY7ofajMF+xc8jyonriTJOnbyxOuxxGDOvKBpPaYGB49XQB1hY38NULfpdD6cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b46909f17d340f2f12dbaee0d51aa66a8b21426e25cd9adb84a04465edec5b6","last_reissued_at":"2026-07-05T09:18:22.917863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:22.917863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07876","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"inkF7oR0Gpv3joV6lZEV1A9IuxSipjuRINgLBqUjDsp0NIZwDGFBnGp46eOUxPCfTR+GQFdmmpV6wdFfQFebCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:24:28.690380Z"},"content_sha256":"c07c4bc53c9a0bb7c0d1bf47790dd136313994bc631548122ec04b3da5dac3a2","schema_version":"1.0","event_id":"sha256:c07c4bc53c9a0bb7c0d1bf47790dd136313994bc631548122ec04b3da5dac3a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NNDJBHYX2NAPF4JNXLXA2UNKM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Improvement using Language Feedback Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dipendra Misra, Marc-Alexandre C\\^ot\\'e, Victor Zhong, Xingdi Yuan","submitted_at":"2024-02-12T18:41:34Z","abstract_excerpt":"We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large Language Models (LLMs) on visual trajectories verbalized to language descriptions. First, by using LFMs to identify desirable behaviour to imitate, we improve in task-completion rate over strong behavioural cloning baselines on three distinct language grounding environments (Touchdown, ScienceWorld, and ALFWorld). Second, LFMs outperform using LLMs as experts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07876","kind":"arxiv","version":6},"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/2402.07876/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":"2026-07-05T09:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Re0fmxLZ4C76YUkIi/1JUTuPK+fjxHR5Fb3nDS5HXVg+y+gnWziVtqqu9StLK4kx3ts3dTOlFQJXve/qabKgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:24:28.691272Z"},"content_sha256":"2ef0a050094465ed9cf8fbde75fa4630cee98286e4ec1cb6fdeab19d928d4790","schema_version":"1.0","event_id":"sha256:2ef0a050094465ed9cf8fbde75fa4630cee98286e4ec1cb6fdeab19d928d4790"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/bundle.json","state_url":"https://pith.science/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/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":"2026-08-17T17:24:28Z","links":{"resolver":"https://pith.science/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2","bundle":"https://pith.science/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/bundle.json","state":"https://pith.science/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNDJBHYX2NAPF4JNXLXA2UNKM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NNDJBHYX2NAPF4JNXLXA2UNKM2","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":"776f0d0e8712177ae9b04011e39dc56fe9b385be1038bc99871916f739e4550d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T18:41:34Z","title_canon_sha256":"6fad1ad812949a1b6b11081376e986472efb510eb27b1f879365d35c083d146b"},"schema_version":"1.0","source":{"id":"2402.07876","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07876","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07876v6","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07876","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"NNDJBHYX2NAP","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"NNDJBHYX2NAPF4JN","created_at":"2026-07-05T09:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"NNDJBHYX","created_at":"2026-07-05T09:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:2ef0a050094465ed9cf8fbde75fa4630cee98286e4ec1cb6fdeab19d928d4790","target":"graph","created_at":"2026-07-05T09:18:22Z","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/2402.07876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large Language Models (LLMs) on visual trajectories verbalized to language descriptions. First, by using LFMs to identify desirable behaviour to imitate, we improve in task-completion rate over strong behavioural cloning baselines on three distinct language grounding environments (Touchdown, ScienceWorld, and ALFWorld). Second, LFMs outperform using LLMs as experts ","authors_text":"Dipendra Misra, Marc-Alexandre C\\^ot\\'e, Victor Zhong, Xingdi Yuan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T18:41:34Z","title":"Policy Improvement using Language Feedback Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07876","kind":"arxiv","version":6},"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:c07c4bc53c9a0bb7c0d1bf47790dd136313994bc631548122ec04b3da5dac3a2","target":"record","created_at":"2026-07-05T09:18:22Z","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":"776f0d0e8712177ae9b04011e39dc56fe9b385be1038bc99871916f739e4550d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T18:41:34Z","title_canon_sha256":"6fad1ad812949a1b6b11081376e986472efb510eb27b1f879365d35c083d146b"},"schema_version":"1.0","source":{"id":"2402.07876","kind":"arxiv","version":6}},"canonical_sha256":"6b46909f17d340f2f12dbaee0d51aa66a8b21426e25cd9adb84a04465edec5b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b46909f17d340f2f12dbaee0d51aa66a8b21426e25cd9adb84a04465edec5b6","first_computed_at":"2026-07-05T09:18:22.917863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:22.917863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tW0PXY5avWYhbWk9yVVT6XDjY7ofajMF+xc8jyonriTJOnbyxOuxxGDOvKBpPaYGB49XQB1hY38NULfpdD6cAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:22.918370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07876","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c07c4bc53c9a0bb7c0d1bf47790dd136313994bc631548122ec04b3da5dac3a2","sha256:2ef0a050094465ed9cf8fbde75fa4630cee98286e4ec1cb6fdeab19d928d4790"],"state_sha256":"70f9717c56591cae891300559f0823ef4f24a6970732a348e0a3ed1a2d16a5fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vv3MLpfAtRxGAzka9hjZ5Msh8Ttck/qGMEKHxGJxcLf36ole07lOckPm6pk8jU6lnBLjF03iRhGL3Tt4KBFxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:24:28.697975Z","bundle_sha256":"c6d949315221e011d6adc7bd84f1c116710e1e003457cb7145f50613b1fb2be1"}}