{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G22PTXE7Z6JSWPIDVJRTHULHVT","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":"ebfd313f4df5e64f4128b53932086bf1cdd19f2f713d9118cebb15a99eb33c9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:22:54Z","title_canon_sha256":"c98ac53815d7d94d4c901d7cbe29c13d6f8c306b987e43d49654ec6dc14ef4a1"},"schema_version":"1.0","source":{"id":"2407.02446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02446","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02446v1","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02446","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"G22PTXE7Z6JS","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"G22PTXE7Z6JSWPID","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"G22PTXE7","created_at":"2026-07-05T08:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:1f962830b286c1682550d5c9876ce97609daacaf8bcbb7e27a1d93d6cbfb4f19","target":"graph","created_at":"2026-07-05T08:39:24Z","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/2407.02446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RLHF-aligned LMs have shown unprecedented ability on both benchmarks and long-form text generation, yet they struggle with one foundational task: next-token prediction. As RLHF models become agent models aimed at interacting with humans, they seem to lose their world modeling -- the ability to predict what comes next in arbitrary documents, which is the foundational training objective of the Base LMs that RLHF adapts.\n  Besides empirically demonstrating this trade-off, we propose a potential explanation: to perform coherent long-form generation, RLHF models restrict randomness via implicit blu","authors_text":"Ari Holtzman, Artidoro Pagnoni, Margaret Li, Peter West, Weijia Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:22:54Z","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02446","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":"sha256:35665637734d4600642f8784e184ff0d9538a49b79349e593747f39d492137c4","target":"record","created_at":"2026-07-05T08:39:24Z","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":"ebfd313f4df5e64f4128b53932086bf1cdd19f2f713d9118cebb15a99eb33c9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:22:54Z","title_canon_sha256":"c98ac53815d7d94d4c901d7cbe29c13d6f8c306b987e43d49654ec6dc14ef4a1"},"schema_version":"1.0","source":{"id":"2407.02446","kind":"arxiv","version":1}},"canonical_sha256":"36b4f9dc9fcf932b3d03aa6333d167acc66febdbc51634c3be54ffb4e2a7142a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36b4f9dc9fcf932b3d03aa6333d167acc66febdbc51634c3be54ffb4e2a7142a","first_computed_at":"2026-07-05T08:39:24.046499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:24.046499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5j8R61pSdyHQ6yt9FxiTuV/Wu+/GzAeiM7QPt5cPNoQG3rEVge6Q7V4yb15hzRy3Z0Hv408kRoD/UEtNyKX1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:24.046906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35665637734d4600642f8784e184ff0d9538a49b79349e593747f39d492137c4","sha256:1f962830b286c1682550d5c9876ce97609daacaf8bcbb7e27a1d93d6cbfb4f19"],"state_sha256":"1433a40c1b89a4757ca4ee8409327e1d51a39fcf9759902fa409a2e8b487e66d"}