{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZDAEGMNB26L7V6MBLIYX7CRBGX","short_pith_number":"pith:ZDAEGMNB","canonical_record":{"source":{"id":"2307.12425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-23T20:43:21Z","cross_cats_sorted":[],"title_canon_sha256":"14c9aa764f1316900dee35d437ad45fc9b62341d4efae4af50ddef2a5aca7344","abstract_canon_sha256":"705e5e6bff2eb25443fe36b12c937b8cff78cd92322538ca6edb1d30d9d91837"},"schema_version":"1.0"},"canonical_sha256":"c8c04331a1d797faf9815a317f8a2135d41474538024ac3f6ae1817846c1b6dd","source":{"kind":"arxiv","id":"2307.12425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12425","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12425v1","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12425","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZDAEGMNB26L7","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZDAEGMNB26L7V6MB","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZDAEGMNB","created_at":"2026-07-05T06:33:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZDAEGMNB26L7V6MBLIYX7CRBGX","target":"record","payload":{"canonical_record":{"source":{"id":"2307.12425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-23T20:43:21Z","cross_cats_sorted":[],"title_canon_sha256":"14c9aa764f1316900dee35d437ad45fc9b62341d4efae4af50ddef2a5aca7344","abstract_canon_sha256":"705e5e6bff2eb25443fe36b12c937b8cff78cd92322538ca6edb1d30d9d91837"},"schema_version":"1.0"},"canonical_sha256":"c8c04331a1d797faf9815a317f8a2135d41474538024ac3f6ae1817846c1b6dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:54.150354Z","signature_b64":"MSrenLex5Vi+0zIiACoEEUZLmctLNHRVsSs7smdP+kyAbohJAAvLd5HXHidx5Fv1wWIQ2B5JKjBvwODs2mlTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c04331a1d797faf9815a317f8a2135d41474538024ac3f6ae1817846c1b6dd","last_reissued_at":"2026-07-05T06:33:54.149818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:54.149818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.12425","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":"2026-07-05T06:33:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3VszelHxON35SEWnDvA5VY9spcadKXd3FK5lf247N6C0gN7BON5ZVg7IDcdRkXAVJgaUVLY1aKrWLWvaJrQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:05:04.628640Z"},"content_sha256":"3324881dd836c25beb1aab0da52a6e79c802ed50caca33f93f008fc266f597ed","schema_version":"1.0","event_id":"sha256:3324881dd836c25beb1aab0da52a6e79c802ed50caca33f93f008fc266f597ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZDAEGMNB26L7V6MBLIYX7CRBGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Effectiveness of Offline RL for Dialogue Response Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ethan R. Elenberg, Felix Wu, Kilian Q. Weinberger, Paloma Sodhi, Ryan McDonald","submitted_at":"2023-07-23T20:43:21Z","abstract_excerpt":"A common training technique for language models is teacher forcing (TF). TF attempts to match human language exactly, even though identical meanings can be expressed in different ways. This motivates use of sequence-level objectives for dialogue response generation. In this paper, we study the efficacy of various offline reinforcement learning (RL) methods to maximize such objectives. We present a comprehensive evaluation across multiple datasets, models, and metrics. Offline RL shows a clear performance improvement over teacher forcing while not inducing training instability or sacrificing pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12425","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/2307.12425/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":"2026-07-05T06:33:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPPgjZbaIZf0Dnz/y1cAdWoEhB56ydpA4UKvJ5zTnf0VFIYOn2EiwidgdL/5tYyIErowR77RPIUp5OC6OeUADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:05:04.629169Z"},"content_sha256":"2eab40132043f4c35ef716fd8e97f60453a016af7e646f88eea3b04ff4050f80","schema_version":"1.0","event_id":"sha256:2eab40132043f4c35ef716fd8e97f60453a016af7e646f88eea3b04ff4050f80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/bundle.json","state_url":"https://pith.science/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/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":"2026-08-20T16:05:04Z","links":{"resolver":"https://pith.science/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX","bundle":"https://pith.science/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/bundle.json","state":"https://pith.science/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDAEGMNB26L7V6MBLIYX7CRBGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZDAEGMNB26L7V6MBLIYX7CRBGX","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":"705e5e6bff2eb25443fe36b12c937b8cff78cd92322538ca6edb1d30d9d91837","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-23T20:43:21Z","title_canon_sha256":"14c9aa764f1316900dee35d437ad45fc9b62341d4efae4af50ddef2a5aca7344"},"schema_version":"1.0","source":{"id":"2307.12425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12425","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12425v1","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12425","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZDAEGMNB26L7","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZDAEGMNB26L7V6MB","created_at":"2026-07-05T06:33:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZDAEGMNB","created_at":"2026-07-05T06:33:54Z"}],"graph_snapshots":[{"event_id":"sha256:2eab40132043f4c35ef716fd8e97f60453a016af7e646f88eea3b04ff4050f80","target":"graph","created_at":"2026-07-05T06:33:54Z","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/2307.12425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common training technique for language models is teacher forcing (TF). TF attempts to match human language exactly, even though identical meanings can be expressed in different ways. This motivates use of sequence-level objectives for dialogue response generation. In this paper, we study the efficacy of various offline reinforcement learning (RL) methods to maximize such objectives. We present a comprehensive evaluation across multiple datasets, models, and metrics. Offline RL shows a clear performance improvement over teacher forcing while not inducing training instability or sacrificing pr","authors_text":"Ethan R. Elenberg, Felix Wu, Kilian Q. Weinberger, Paloma Sodhi, Ryan McDonald","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-23T20:43:21Z","title":"On the Effectiveness of Offline RL for Dialogue Response Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12425","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":"sha256:3324881dd836c25beb1aab0da52a6e79c802ed50caca33f93f008fc266f597ed","target":"record","created_at":"2026-07-05T06:33:54Z","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":"705e5e6bff2eb25443fe36b12c937b8cff78cd92322538ca6edb1d30d9d91837","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-23T20:43:21Z","title_canon_sha256":"14c9aa764f1316900dee35d437ad45fc9b62341d4efae4af50ddef2a5aca7344"},"schema_version":"1.0","source":{"id":"2307.12425","kind":"arxiv","version":1}},"canonical_sha256":"c8c04331a1d797faf9815a317f8a2135d41474538024ac3f6ae1817846c1b6dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8c04331a1d797faf9815a317f8a2135d41474538024ac3f6ae1817846c1b6dd","first_computed_at":"2026-07-05T06:33:54.149818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:54.149818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MSrenLex5Vi+0zIiACoEEUZLmctLNHRVsSs7smdP+kyAbohJAAvLd5HXHidx5Fv1wWIQ2B5JKjBvwODs2mlTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:54.150354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3324881dd836c25beb1aab0da52a6e79c802ed50caca33f93f008fc266f597ed","sha256:2eab40132043f4c35ef716fd8e97f60453a016af7e646f88eea3b04ff4050f80"],"state_sha256":"f1b82cd3e34125ed29416316c6d1e218755b652f3bb8202236538cedbd5dbabf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EoWWuvqsjO5rLF3UxZdnPubToUqvJjC+v6Z499dzkU3186Kx3/ypJwTE1p81h7VYtk13WEY2IN4BGTh+xRYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T16:05:04.635510Z","bundle_sha256":"4c62632ecf865f620cb3a0999864634c9bab5e1afaf2adf5f96e824df422ddb2"}}