{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XZ4426VQUESLYEMTLIUYL5BHCP","short_pith_number":"pith:XZ4426VQ","canonical_record":{"source":{"id":"2410.12160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T01:49:03Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"4f13810c8732db5d7ddd7dc96f543dda5e2d7354eaa034edc11dd9038e783d96","abstract_canon_sha256":"e5ea9cd6c23acb177451f7467cf19e425a9f6728a0380ec90dbdce762f780d0c"},"schema_version":"1.0"},"canonical_sha256":"be79cd7ab0a124bc11935a2985f42713f5c8f82267d1df923c19d6c0e9e98faf","source":{"kind":"arxiv","id":"2410.12160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12160","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12160v1","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12160","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"XZ4426VQUESL","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"XZ4426VQUESLYEMT","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"XZ4426VQ","created_at":"2026-07-05T09:21:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XZ4426VQUESLYEMTLIUYL5BHCP","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T01:49:03Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"4f13810c8732db5d7ddd7dc96f543dda5e2d7354eaa034edc11dd9038e783d96","abstract_canon_sha256":"e5ea9cd6c23acb177451f7467cf19e425a9f6728a0380ec90dbdce762f780d0c"},"schema_version":"1.0"},"canonical_sha256":"be79cd7ab0a124bc11935a2985f42713f5c8f82267d1df923c19d6c0e9e98faf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:15.066374Z","signature_b64":"9uyxsxLd+xma+7Kzd4MofrwjLl1BvesBoUdYMHpgxHCDJmavzm7icSKLnaE5lV77CoR9V0dPtlOmfDZmocojCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be79cd7ab0a124bc11935a2985f42713f5c8f82267d1df923c19d6c0e9e98faf","last_reissued_at":"2026-07-05T09:21:15.066020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:15.066020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12160","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":"2026-07-05T09:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPW+2sY+hg95Brh0kkGgG4M3XaJLsMVk6alxxxyt3BHm1fVE6yGff+4gwvFfUzvd6MNsK3MfikZ2bn2prNStBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:53:46.795040Z"},"content_sha256":"1f83470e3f3aa6a22fbf4c6f70ac3cbf102f4d5c7ce750977252044362974a53","schema_version":"1.0","event_id":"sha256:1f83470e3f3aa6a22fbf4c6f70ac3cbf102f4d5c7ce750977252044362974a53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XZ4426VQUESLYEMTLIUYL5BHCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ertai Luo, Shuo Han, Shuo Wu, Yansong Li, Yu Wu, Zeyu Dong","submitted_at":"2024-10-16T01:49:03Z","abstract_excerpt":"Reinforcement learning (RL) algorithms can be divided into two classes: model-free algorithms, which are sample-inefficient, and model-based algorithms, which suffer from model bias. Dyna-style algorithms combine these two approaches by using simulated data from an estimated environmental model to accelerate model-free training. However, their efficiency is compromised when the estimated model is inaccurate. Previous works address this issue by using model ensembles or pretraining the estimated model with data collected from the real environment, increasing computational and sample complexity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12160","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/2410.12160/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":"2026-07-05T09:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yeRMp0mPmwA9QZtCl20Bcq0nIFvnvzSzNKLEkxr2JCRDmFuLYEBQvv38+Kx13OoSlieZo1WnIkusagozdGdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:53:46.795590Z"},"content_sha256":"c24f624f7e59ccb3b57c7df77eca129a9db5cd1e649bd199ed9abaf0e33536cf","schema_version":"1.0","event_id":"sha256:c24f624f7e59ccb3b57c7df77eca129a9db5cd1e649bd199ed9abaf0e33536cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZ4426VQUESLYEMTLIUYL5BHCP/bundle.json","state_url":"https://pith.science/pith/XZ4426VQUESLYEMTLIUYL5BHCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZ4426VQUESLYEMTLIUYL5BHCP/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":"2026-08-19T10:53:46Z","links":{"resolver":"https://pith.science/pith/XZ4426VQUESLYEMTLIUYL5BHCP","bundle":"https://pith.science/pith/XZ4426VQUESLYEMTLIUYL5BHCP/bundle.json","state":"https://pith.science/pith/XZ4426VQUESLYEMTLIUYL5BHCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZ4426VQUESLYEMTLIUYL5BHCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XZ4426VQUESLYEMTLIUYL5BHCP","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":"e5ea9cd6c23acb177451f7467cf19e425a9f6728a0380ec90dbdce762f780d0c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T01:49:03Z","title_canon_sha256":"4f13810c8732db5d7ddd7dc96f543dda5e2d7354eaa034edc11dd9038e783d96"},"schema_version":"1.0","source":{"id":"2410.12160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12160","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12160v1","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12160","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"XZ4426VQUESL","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"XZ4426VQUESLYEMT","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"XZ4426VQ","created_at":"2026-07-05T09:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:c24f624f7e59ccb3b57c7df77eca129a9db5cd1e649bd199ed9abaf0e33536cf","target":"graph","created_at":"2026-07-05T09:21:15Z","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/2410.12160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) algorithms can be divided into two classes: model-free algorithms, which are sample-inefficient, and model-based algorithms, which suffer from model bias. Dyna-style algorithms combine these two approaches by using simulated data from an estimated environmental model to accelerate model-free training. However, their efficiency is compromised when the estimated model is inaccurate. Previous works address this issue by using model ensembles or pretraining the estimated model with data collected from the real environment, increasing computational and sample complexity.","authors_text":"Ertai Luo, Shuo Han, Shuo Wu, Yansong Li, Yu Wu, Zeyu Dong","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T01:49:03Z","title":"When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12160","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":"sha256:1f83470e3f3aa6a22fbf4c6f70ac3cbf102f4d5c7ce750977252044362974a53","target":"record","created_at":"2026-07-05T09:21:15Z","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":"e5ea9cd6c23acb177451f7467cf19e425a9f6728a0380ec90dbdce762f780d0c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T01:49:03Z","title_canon_sha256":"4f13810c8732db5d7ddd7dc96f543dda5e2d7354eaa034edc11dd9038e783d96"},"schema_version":"1.0","source":{"id":"2410.12160","kind":"arxiv","version":1}},"canonical_sha256":"be79cd7ab0a124bc11935a2985f42713f5c8f82267d1df923c19d6c0e9e98faf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be79cd7ab0a124bc11935a2985f42713f5c8f82267d1df923c19d6c0e9e98faf","first_computed_at":"2026-07-05T09:21:15.066020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:15.066020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9uyxsxLd+xma+7Kzd4MofrwjLl1BvesBoUdYMHpgxHCDJmavzm7icSKLnaE5lV77CoR9V0dPtlOmfDZmocojCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:15.066374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f83470e3f3aa6a22fbf4c6f70ac3cbf102f4d5c7ce750977252044362974a53","sha256:c24f624f7e59ccb3b57c7df77eca129a9db5cd1e649bd199ed9abaf0e33536cf"],"state_sha256":"29e258a688c1eafc0a5732855218af57b2795c16a8368350d5ce3328540b737e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eU/ZxwFlZUr9XxjpW9jXvKxesp+DvrDmc3b5I/tXaCwpU8AJ+4We+le2FBF95e98Un0fPnBQHtJ2O4swIVq9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:53:46.801582Z","bundle_sha256":"645e97a17c7c46d48e9e1bc944cf43be92f05728a7020ed5a6546d94d5034b66"}}