{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O3Z3M4MB3ZCYSVFUVHE4R5EISO","short_pith_number":"pith:O3Z3M4MB","canonical_record":{"source":{"id":"2412.05766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T00:21:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0583cd9888792a81a746ed5bd6a0bba69ba40c565cd7171d4f2ece256dd16961","abstract_canon_sha256":"025008affaba1b2da1e105c61be22cf602ce2c192035c3dff1f8d514972517c8"},"schema_version":"1.0"},"canonical_sha256":"76f3b67181de458954b4a9c9c8f48893adc9ec0cc5316cddc344e3b5a3fec122","source":{"kind":"arxiv","id":"2412.05766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05766","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05766v1","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05766","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"O3Z3M4MB3ZCY","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"O3Z3M4MB3ZCYSVFU","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"O3Z3M4MB","created_at":"2026-07-05T09:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O3Z3M4MB3ZCYSVFUVHE4R5EISO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T00:21:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0583cd9888792a81a746ed5bd6a0bba69ba40c565cd7171d4f2ece256dd16961","abstract_canon_sha256":"025008affaba1b2da1e105c61be22cf602ce2c192035c3dff1f8d514972517c8"},"schema_version":"1.0"},"canonical_sha256":"76f3b67181de458954b4a9c9c8f48893adc9ec0cc5316cddc344e3b5a3fec122","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:08.531128Z","signature_b64":"3+4pqRoh770anPO/wql8Cx3nBV5WHvbxAa1A51h4FP4mpsy9wrXBFrPQUFpzgwZFIC774c9h6Cnyw1EV2GJ2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76f3b67181de458954b4a9c9c8f48893adc9ec0cc5316cddc344e3b5a3fec122","last_reissued_at":"2026-07-05T09:46:08.530693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:08.530693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05766","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":"2026-07-05T09:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmPtLHdfh269RcWtff0RvHo+mmLtTE1V1pCyc8+EZR47/jg772dvltXUQ9cTZzAMj54MzhSeYcQJTdJqNJgrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:37:11.369650Z"},"content_sha256":"c2d622e384c0d077640947b6892e393993f3b4442ae783d4508f7df93ad6ab0b","schema_version":"1.0","event_id":"sha256:c2d622e384c0d077640947b6892e393993f3b4442ae783d4508f7df93ad6ab0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O3Z3M4MB3ZCYSVFUVHE4R5EISO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Isaac Kauvar, Miles Hutson, Nick Haber","submitted_at":"2024-12-08T00:21:37Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly predictable, but irrelevant to learning a good policy. Such scenarios can lead the model to exhaust its capacity on meaningless content, at the cost of neglecting important environment dynamics. While existing approaches attempt to solve this problem, we highlight its continuing impact on leading MBRL methods -- including DreamerV3 and DreamerPro -- with a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05766","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/2412.05766/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":"2026-07-05T09:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CXmH9s7cvP4lCLBy8JIwxfYn09wH12Hja8zqwVTg/jkq4xEPmiD6fhpzfBZc+HSrti/Qk8AUdkHP2+YZUMQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:37:11.370575Z"},"content_sha256":"8f28a2faacd1187e68baeb5b9dd2ecd27b07870f53c20b04855cdff8399cc730","schema_version":"1.0","event_id":"sha256:8f28a2faacd1187e68baeb5b9dd2ecd27b07870f53c20b04855cdff8399cc730"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/bundle.json","state_url":"https://pith.science/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/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":"2026-08-12T08:37:11Z","links":{"resolver":"https://pith.science/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO","bundle":"https://pith.science/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/bundle.json","state":"https://pith.science/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O3Z3M4MB3ZCYSVFUVHE4R5EISO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O3Z3M4MB3ZCYSVFUVHE4R5EISO","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":"025008affaba1b2da1e105c61be22cf602ce2c192035c3dff1f8d514972517c8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T00:21:37Z","title_canon_sha256":"0583cd9888792a81a746ed5bd6a0bba69ba40c565cd7171d4f2ece256dd16961"},"schema_version":"1.0","source":{"id":"2412.05766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05766","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05766v1","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05766","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"O3Z3M4MB3ZCY","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"O3Z3M4MB3ZCYSVFU","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"O3Z3M4MB","created_at":"2026-07-05T09:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:8f28a2faacd1187e68baeb5b9dd2ecd27b07870f53c20b04855cdff8399cc730","target":"graph","created_at":"2026-07-05T09:46:08Z","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/2412.05766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly predictable, but irrelevant to learning a good policy. Such scenarios can lead the model to exhaust its capacity on meaningless content, at the cost of neglecting important environment dynamics. While existing approaches attempt to solve this problem, we highlight its continuing impact on leading MBRL methods -- including DreamerV3 and DreamerPro -- with a novel","authors_text":"Isaac Kauvar, Miles Hutson, Nick Haber","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T00:21:37Z","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05766","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:c2d622e384c0d077640947b6892e393993f3b4442ae783d4508f7df93ad6ab0b","target":"record","created_at":"2026-07-05T09:46:08Z","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":"025008affaba1b2da1e105c61be22cf602ce2c192035c3dff1f8d514972517c8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T00:21:37Z","title_canon_sha256":"0583cd9888792a81a746ed5bd6a0bba69ba40c565cd7171d4f2ece256dd16961"},"schema_version":"1.0","source":{"id":"2412.05766","kind":"arxiv","version":1}},"canonical_sha256":"76f3b67181de458954b4a9c9c8f48893adc9ec0cc5316cddc344e3b5a3fec122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76f3b67181de458954b4a9c9c8f48893adc9ec0cc5316cddc344e3b5a3fec122","first_computed_at":"2026-07-05T09:46:08.530693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:08.530693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+4pqRoh770anPO/wql8Cx3nBV5WHvbxAa1A51h4FP4mpsy9wrXBFrPQUFpzgwZFIC774c9h6Cnyw1EV2GJ2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:08.531128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2d622e384c0d077640947b6892e393993f3b4442ae783d4508f7df93ad6ab0b","sha256:8f28a2faacd1187e68baeb5b9dd2ecd27b07870f53c20b04855cdff8399cc730"],"state_sha256":"dbda78d81493c1e4d0b91221869aeb94c9ee0846e68b0c16232cc7d81fe8fe4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cho3gqWLWeYRtDz+HW109W8oN0BctDytAIShsT9EjcqxfGHZeSAK/2+CRjsnMGAB8cZV/OJhFW9UDTHbMzEqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:37:11.377357Z","bundle_sha256":"b4a540b260cb946e81aef87a713a137afdd77dcebd3a89361837579b345e57c2"}}