{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EVN5LVHAEVBN66LRJ7FCLTWKFK","short_pith_number":"pith:EVN5LVHA","canonical_record":{"source":{"id":"2412.14312","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T20:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"6e0b858655d1ba77a82ac6a2c289131af61fc93bd12c032bd3a7b96437fd7f67","abstract_canon_sha256":"93c57673700d421209cbe08269cb413b09ecf5465736204ce8a92ae2840629cf"},"schema_version":"1.0"},"canonical_sha256":"255bd5d4e02542df79714fca25ceca2aaaf13a048b92bc287a42ed92ae14aa0f","source":{"kind":"arxiv","id":"2412.14312","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14312","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14312v3","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14312","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_12","alias_value":"EVN5LVHAEVBN","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_16","alias_value":"EVN5LVHAEVBN66LR","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_8","alias_value":"EVN5LVHA","created_at":"2026-07-05T11:25:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EVN5LVHAEVBN66LRJ7FCLTWKFK","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14312","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T20:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"6e0b858655d1ba77a82ac6a2c289131af61fc93bd12c032bd3a7b96437fd7f67","abstract_canon_sha256":"93c57673700d421209cbe08269cb413b09ecf5465736204ce8a92ae2840629cf"},"schema_version":"1.0"},"canonical_sha256":"255bd5d4e02542df79714fca25ceca2aaaf13a048b92bc287a42ed92ae14aa0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:06.781778Z","signature_b64":"9oSL8KGq+m2wspZwNLB5CDhQ3sAPmZ9JGvwfzvXAGvw0v1V7jMgNyf0dRFuiX72eYdBl2Vzy/2cRi4RMMtrEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"255bd5d4e02542df79714fca25ceca2aaaf13a048b92bc287a42ed92ae14aa0f","last_reissued_at":"2026-07-05T11:25:06.781284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:06.781284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14312","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V26Vxfvm4m54RpmW2CV5y8RLTnAggzh8irPTSAfS4aKjFAofrkxXL0RCukP5pnK22VLwVwefZUzRgjWAjGWABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:38:14.970455Z"},"content_sha256":"23022fde7efb3cea58f380405b5500bb1326693f622cc6454dabb3427ab08c7d","schema_version":"1.0","event_id":"sha256:23022fde7efb3cea58f380405b5500bb1326693f622cc6454dabb3427ab08c7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EVN5LVHAEVBN66LRJ7FCLTWKFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brett Barkley, David Fridovich-Keil","submitted_at":"2024-12-18T20:25:04Z","abstract_excerpt":"Dyna-style off-policy model-based reinforcement learning (DMBRL) algorithms are a family of techniques for generating synthetic state transition data and thereby enhancing the sample efficiency of off-policy RL algorithms. This paper identifies and investigates a surprising performance gap observed when applying DMBRL algorithms across different benchmark environments with proprioceptive observations. We show that, while DMBRL algorithms perform well in OpenAI Gym, their performance can drop significantly in DeepMind Control Suite (DMC), even though these settings offer similar tasks and ident"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14312","kind":"arxiv","version":3},"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/2412.14312/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":"2026-07-05T11:25:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sge9H0xpTHwBK/HK9MkHE8+iVO7oJN7nn4xVOgQLKPeDOHs+JBf4vUOwL5S4twMdVx112YgC7K5aFTO9Ihg6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:38:14.971039Z"},"content_sha256":"d3f9235226654265d83288d5f6ce3f62fba5d189e72a2be26c04597c7d6175bc","schema_version":"1.0","event_id":"sha256:d3f9235226654265d83288d5f6ce3f62fba5d189e72a2be26c04597c7d6175bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/bundle.json","state_url":"https://pith.science/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/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":"2026-08-19T05:38:14Z","links":{"resolver":"https://pith.science/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK","bundle":"https://pith.science/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/bundle.json","state":"https://pith.science/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EVN5LVHAEVBN66LRJ7FCLTWKFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EVN5LVHAEVBN66LRJ7FCLTWKFK","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":"93c57673700d421209cbe08269cb413b09ecf5465736204ce8a92ae2840629cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T20:25:04Z","title_canon_sha256":"6e0b858655d1ba77a82ac6a2c289131af61fc93bd12c032bd3a7b96437fd7f67"},"schema_version":"1.0","source":{"id":"2412.14312","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14312","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14312v3","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14312","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_12","alias_value":"EVN5LVHAEVBN","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_16","alias_value":"EVN5LVHAEVBN66LR","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_8","alias_value":"EVN5LVHA","created_at":"2026-07-05T11:25:06Z"}],"graph_snapshots":[{"event_id":"sha256:d3f9235226654265d83288d5f6ce3f62fba5d189e72a2be26c04597c7d6175bc","target":"graph","created_at":"2026-07-05T11:25:06Z","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/2412.14312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dyna-style off-policy model-based reinforcement learning (DMBRL) algorithms are a family of techniques for generating synthetic state transition data and thereby enhancing the sample efficiency of off-policy RL algorithms. This paper identifies and investigates a surprising performance gap observed when applying DMBRL algorithms across different benchmark environments with proprioceptive observations. We show that, while DMBRL algorithms perform well in OpenAI Gym, their performance can drop significantly in DeepMind Control Suite (DMC), even though these settings offer similar tasks and ident","authors_text":"Brett Barkley, David Fridovich-Keil","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T20:25:04Z","title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14312","kind":"arxiv","version":3},"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":"sha256:23022fde7efb3cea58f380405b5500bb1326693f622cc6454dabb3427ab08c7d","target":"record","created_at":"2026-07-05T11:25:06Z","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":"93c57673700d421209cbe08269cb413b09ecf5465736204ce8a92ae2840629cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T20:25:04Z","title_canon_sha256":"6e0b858655d1ba77a82ac6a2c289131af61fc93bd12c032bd3a7b96437fd7f67"},"schema_version":"1.0","source":{"id":"2412.14312","kind":"arxiv","version":3}},"canonical_sha256":"255bd5d4e02542df79714fca25ceca2aaaf13a048b92bc287a42ed92ae14aa0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"255bd5d4e02542df79714fca25ceca2aaaf13a048b92bc287a42ed92ae14aa0f","first_computed_at":"2026-07-05T11:25:06.781284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:06.781284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9oSL8KGq+m2wspZwNLB5CDhQ3sAPmZ9JGvwfzvXAGvw0v1V7jMgNyf0dRFuiX72eYdBl2Vzy/2cRi4RMMtrEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:06.781778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14312","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23022fde7efb3cea58f380405b5500bb1326693f622cc6454dabb3427ab08c7d","sha256:d3f9235226654265d83288d5f6ce3f62fba5d189e72a2be26c04597c7d6175bc"],"state_sha256":"32175051d5f832e1cfc5f703e903bcdaa0e4d79109a5f774c25f340a9c026bdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtFLdf1FmjZZGt4onh9Ui61uzYlMH9Dh8AWB9gSqLpxihzSeskW20yhFiCC2Do/ikaLy/ESHZu/E3VYqQU3/BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:38:14.976930Z","bundle_sha256":"554e05a68be240953b6782d461db36493bdc20ae879400ef129289d4f0ce532a"}}