{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CA3OVUO52HWOEEG3G2ICLZ22I4","short_pith_number":"pith:CA3OVUO5","canonical_record":{"source":{"id":"2310.03716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T17:38:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2b266e063771a60007e136e98226781d71c5cf54ac23b02f18aeca2b94e25d04","abstract_canon_sha256":"dcec4162a9a147be5d44e8d3cd088a0276b48b5194092d57749b23f23c89390e"},"schema_version":"1.0"},"canonical_sha256":"1036ead1ddd1ece210db369025e75a4708c18c603d48c4fae7df7cdaf67862b0","source":{"kind":"arxiv","id":"2310.03716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03716","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03716v2","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03716","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_12","alias_value":"CA3OVUO52HWO","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_16","alias_value":"CA3OVUO52HWOEEG3","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_8","alias_value":"CA3OVUO5","created_at":"2026-07-05T08:42:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CA3OVUO52HWOEEG3G2ICLZ22I4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T17:38:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2b266e063771a60007e136e98226781d71c5cf54ac23b02f18aeca2b94e25d04","abstract_canon_sha256":"dcec4162a9a147be5d44e8d3cd088a0276b48b5194092d57749b23f23c89390e"},"schema_version":"1.0"},"canonical_sha256":"1036ead1ddd1ece210db369025e75a4708c18c603d48c4fae7df7cdaf67862b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:30.485330Z","signature_b64":"dKVhT11HQL3JFT92mJmc/otiLiOttLDfbxVjoeGIXbolQxwOxIkDxjELbyqr2eL94Pi5bXWzVEfrXwXKbDy6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1036ead1ddd1ece210db369025e75a4708c18c603d48c4fae7df7cdaf67862b0","last_reissued_at":"2026-07-05T08:42:30.484852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:30.484852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03716","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRsyo9Wt/8N+NPD8WgudLAyQrEyeguPy8+Z8V2rcxA4WoCS/6Akj9gu6wSOhGCHIgUtrmCGebPJGxMwblO65DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:13:11.736504Z"},"content_sha256":"ce7b9af29191f6cfd52b1a0298609bf4976b7afa61c6c8948963e7a41a525228","schema_version":"1.0","event_id":"sha256:ce7b9af29191f6cfd52b1a0298609bf4976b7afa61c6c8948963e7a41a525228"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CA3OVUO52HWOEEG3G2ICLZ22I4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Long Way to Go: Investigating Length Correlations in RLHF","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jiacheng Xu, Prasann Singhal, Tanya Goyal","submitted_at":"2023-10-05T17:38:28Z","abstract_excerpt":"Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for \"helpfulness\" in tasks like dialogue and web question answering. Alongside these improvements, however, RLHF also often drives models to produce longer outputs. This paper demonstrates, on three diverse settings, that optimizing for response length is, much more than previously thought, a significant factor behind RLHF. Studying the strategies RL optimization uses to maximize reward, we find improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03716","kind":"arxiv","version":2},"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/2310.03716/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":"2026-07-05T08:42:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAhsY9iVx8CPI8EdMRC/A95/SwlQmgcAvn5j2OxBLKk5n7fyKdhuzQJMAU7GlA8WQ5Tlz0/28sRzmZyvhH3rAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:13:11.737091Z"},"content_sha256":"fc68f1751118afa75bd2295b0bbd2f9419a8ff7d8488750b26aaaf56656e19ba","schema_version":"1.0","event_id":"sha256:fc68f1751118afa75bd2295b0bbd2f9419a8ff7d8488750b26aaaf56656e19ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/bundle.json","state_url":"https://pith.science/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/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":"2026-08-06T08:13:11Z","links":{"resolver":"https://pith.science/pith/CA3OVUO52HWOEEG3G2ICLZ22I4","bundle":"https://pith.science/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/bundle.json","state":"https://pith.science/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CA3OVUO52HWOEEG3G2ICLZ22I4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CA3OVUO52HWOEEG3G2ICLZ22I4","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":"dcec4162a9a147be5d44e8d3cd088a0276b48b5194092d57749b23f23c89390e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T17:38:28Z","title_canon_sha256":"2b266e063771a60007e136e98226781d71c5cf54ac23b02f18aeca2b94e25d04"},"schema_version":"1.0","source":{"id":"2310.03716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03716","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03716v2","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03716","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_12","alias_value":"CA3OVUO52HWO","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_16","alias_value":"CA3OVUO52HWOEEG3","created_at":"2026-07-05T08:42:30Z"},{"alias_kind":"pith_short_8","alias_value":"CA3OVUO5","created_at":"2026-07-05T08:42:30Z"}],"graph_snapshots":[{"event_id":"sha256:fc68f1751118afa75bd2295b0bbd2f9419a8ff7d8488750b26aaaf56656e19ba","target":"graph","created_at":"2026-07-05T08:42:30Z","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/2310.03716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for \"helpfulness\" in tasks like dialogue and web question answering. Alongside these improvements, however, RLHF also often drives models to produce longer outputs. This paper demonstrates, on three diverse settings, that optimizing for response length is, much more than previously thought, a significant factor behind RLHF. Studying the strategies RL optimization uses to maximize reward, we find improv","authors_text":"Greg Durrett, Jiacheng Xu, Prasann Singhal, Tanya Goyal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T17:38:28Z","title":"A Long Way to Go: Investigating Length Correlations in RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03716","kind":"arxiv","version":2},"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:ce7b9af29191f6cfd52b1a0298609bf4976b7afa61c6c8948963e7a41a525228","target":"record","created_at":"2026-07-05T08:42:30Z","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":"dcec4162a9a147be5d44e8d3cd088a0276b48b5194092d57749b23f23c89390e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T17:38:28Z","title_canon_sha256":"2b266e063771a60007e136e98226781d71c5cf54ac23b02f18aeca2b94e25d04"},"schema_version":"1.0","source":{"id":"2310.03716","kind":"arxiv","version":2}},"canonical_sha256":"1036ead1ddd1ece210db369025e75a4708c18c603d48c4fae7df7cdaf67862b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1036ead1ddd1ece210db369025e75a4708c18c603d48c4fae7df7cdaf67862b0","first_computed_at":"2026-07-05T08:42:30.484852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:30.484852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dKVhT11HQL3JFT92mJmc/otiLiOttLDfbxVjoeGIXbolQxwOxIkDxjELbyqr2eL94Pi5bXWzVEfrXwXKbDy6Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:30.485330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce7b9af29191f6cfd52b1a0298609bf4976b7afa61c6c8948963e7a41a525228","sha256:fc68f1751118afa75bd2295b0bbd2f9419a8ff7d8488750b26aaaf56656e19ba"],"state_sha256":"ea75bae079b1fe2bdd7915195fe9327a63ffa816c07ea3f8e59b90a7e06d3235"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"58lb1HEDBmLCs2DianPaiYNJ4AJS+by4OXy4/WAzok7zJu0/WVoF87Bo8l25kWv/x0VAY11gFTHVw8I4b2dkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:13:11.741169Z","bundle_sha256":"b8bc1edff74c367f01c71ddbb2b86b675700cea29f950c06e5821e776792f1dd"}}