{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FBN5NBCQTH6XR6FKUVIM2V6NVB","short_pith_number":"pith:FBN5NBCQ","canonical_record":{"source":{"id":"2402.12527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T20:38:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fe126b790e7e8340d9240fabf911e832f33c8d152d5635e7ad3288dea880628","abstract_canon_sha256":"3bd9114dd1d92c87135f99be1bf740d4cee0bae2ab83db246bd2bf99ec03bfe8"},"schema_version":"1.0"},"canonical_sha256":"285bd6845099fd78f8aaa550cd57cda874159b0a6dde6fc59827497a9624534c","source":{"kind":"arxiv","id":"2402.12527","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12527","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12527v2","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12527","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"FBN5NBCQTH6X","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"FBN5NBCQTH6XR6FK","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"FBN5NBCQ","created_at":"2026-07-05T09:42:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FBN5NBCQTH6XR6FKUVIM2V6NVB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T20:38:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fe126b790e7e8340d9240fabf911e832f33c8d152d5635e7ad3288dea880628","abstract_canon_sha256":"3bd9114dd1d92c87135f99be1bf740d4cee0bae2ab83db246bd2bf99ec03bfe8"},"schema_version":"1.0"},"canonical_sha256":"285bd6845099fd78f8aaa550cd57cda874159b0a6dde6fc59827497a9624534c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:23.057522Z","signature_b64":"QHbN4eCqcZufqM4wYgGSUARWF/UvZsS9b2ZuG99B4utXF+pMb6McruWCrxbfORQk7DHH4WBI/+Jo32qRfqJxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285bd6845099fd78f8aaa550cd57cda874159b0a6dde6fc59827497a9624534c","last_reissued_at":"2026-07-05T09:42:23.057060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:23.057060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12527","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":"2026-07-05T09:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCDOxnCFWSGkv7B3zAFFlObZeIHCuQ6MYBMFSR6MVUjb8bn/41UgMjj42ZZSJ/X6eTxoLWp8pvwVl9OmjO+dDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:53.798616Z"},"content_sha256":"fc4f09f5f46854da09bdf70661af0f77a4e87a2d2f6453af508897782b5efe9b","schema_version":"1.0","event_id":"sha256:fc4f09f5f46854da09bdf70661af0f77a4e87a2d2f6453af508897782b5efe9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FBN5NBCQTH6XR6FKUVIM2V6NVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anya Sims, Cong Lu, Jakob Foerster, Yee Whye Teh","submitted_at":"2024-02-19T20:38:00Z","abstract_excerpt":"Offline reinforcement learning aims to train agents from pre-collected datasets. However, this comes with the added challenge of estimating the value of behaviors not covered in the dataset. Model-based methods offer a potential solution by training an approximate dynamics model, which then allows collection of additional synthetic data via rollouts in this model. The prevailing theory treats this approach as online RL in an approximate dynamics model, and any remaining performance gap is therefore understood as being due to dynamics model errors. In this paper, we analyze this assumption and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12527","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/2402.12527/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":"2026-07-05T09:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iTL3Rxg0tXVpmTCsezzqpLNk16tLeQ4F3adNqjqMSHi8HP2zI29fgq026zBQmbGAXi9SMaOybcAhoahPQ3yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:53.799106Z"},"content_sha256":"a81d00b0fe8007b228df708aada0f3996d0c6cff12fdf3cc8de524f6d0d4f899","schema_version":"1.0","event_id":"sha256:a81d00b0fe8007b228df708aada0f3996d0c6cff12fdf3cc8de524f6d0d4f899"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/bundle.json","state_url":"https://pith.science/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/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":"2026-08-06T03:05:53Z","links":{"resolver":"https://pith.science/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB","bundle":"https://pith.science/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/bundle.json","state":"https://pith.science/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBN5NBCQTH6XR6FKUVIM2V6NVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FBN5NBCQTH6XR6FKUVIM2V6NVB","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":"3bd9114dd1d92c87135f99be1bf740d4cee0bae2ab83db246bd2bf99ec03bfe8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T20:38:00Z","title_canon_sha256":"0fe126b790e7e8340d9240fabf911e832f33c8d152d5635e7ad3288dea880628"},"schema_version":"1.0","source":{"id":"2402.12527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12527","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12527v2","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12527","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"FBN5NBCQTH6X","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"FBN5NBCQTH6XR6FK","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"FBN5NBCQ","created_at":"2026-07-05T09:42:23Z"}],"graph_snapshots":[{"event_id":"sha256:a81d00b0fe8007b228df708aada0f3996d0c6cff12fdf3cc8de524f6d0d4f899","target":"graph","created_at":"2026-07-05T09:42:23Z","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/2402.12527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning aims to train agents from pre-collected datasets. However, this comes with the added challenge of estimating the value of behaviors not covered in the dataset. Model-based methods offer a potential solution by training an approximate dynamics model, which then allows collection of additional synthetic data via rollouts in this model. The prevailing theory treats this approach as online RL in an approximate dynamics model, and any remaining performance gap is therefore understood as being due to dynamics model errors. In this paper, we analyze this assumption and ","authors_text":"Anya Sims, Cong Lu, Jakob Foerster, Yee Whye Teh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T20:38:00Z","title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12527","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:fc4f09f5f46854da09bdf70661af0f77a4e87a2d2f6453af508897782b5efe9b","target":"record","created_at":"2026-07-05T09:42:23Z","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":"3bd9114dd1d92c87135f99be1bf740d4cee0bae2ab83db246bd2bf99ec03bfe8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T20:38:00Z","title_canon_sha256":"0fe126b790e7e8340d9240fabf911e832f33c8d152d5635e7ad3288dea880628"},"schema_version":"1.0","source":{"id":"2402.12527","kind":"arxiv","version":2}},"canonical_sha256":"285bd6845099fd78f8aaa550cd57cda874159b0a6dde6fc59827497a9624534c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"285bd6845099fd78f8aaa550cd57cda874159b0a6dde6fc59827497a9624534c","first_computed_at":"2026-07-05T09:42:23.057060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:23.057060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHbN4eCqcZufqM4wYgGSUARWF/UvZsS9b2ZuG99B4utXF+pMb6McruWCrxbfORQk7DHH4WBI/+Jo32qRfqJxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:23.057522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc4f09f5f46854da09bdf70661af0f77a4e87a2d2f6453af508897782b5efe9b","sha256:a81d00b0fe8007b228df708aada0f3996d0c6cff12fdf3cc8de524f6d0d4f899"],"state_sha256":"4b3f3f72900ae256eddf00f3f645d762febba1368c1a27bbdab4ef73534c31df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"phLCTULYqLwOt9Zg6BUPaggeMI2iGti4ZMSOOwvSMb6i7zbuOqfoDhTcMtSFgDoZ3sT6VLWScG0qfORihKFpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:05:53.802366Z","bundle_sha256":"4a253d57f8524cdb45a4fbbbd67ff3cdcf353d2006c9f7400cd8595da49c9069"}}