{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2NUMDWTBS37H23QOFJB4UTTVL6","short_pith_number":"pith:2NUMDWTB","canonical_record":{"source":{"id":"2206.02902","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"348cccfd9cb10937621dda354a43ddb74ad8b96a8ec9ee2f513675820fe9564d","abstract_canon_sha256":"99a4e47e20f0879c7e33f21c4daab2333b7e85082ec7ef8e272b371f20722bd3"},"schema_version":"1.0"},"canonical_sha256":"d368c1da6196fe7d6e0e2a43ca4e755fb981f6e2c614dc1f2483d5a3a36077b2","source":{"kind":"arxiv","id":"2206.02902","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02902","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02902v5","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02902","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_12","alias_value":"2NUMDWTBS37H","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_16","alias_value":"2NUMDWTBS37H23QO","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_8","alias_value":"2NUMDWTB","created_at":"2026-07-05T07:49:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2NUMDWTBS37H23QOFJB4UTTVL6","target":"record","payload":{"canonical_record":{"source":{"id":"2206.02902","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"348cccfd9cb10937621dda354a43ddb74ad8b96a8ec9ee2f513675820fe9564d","abstract_canon_sha256":"99a4e47e20f0879c7e33f21c4daab2333b7e85082ec7ef8e272b371f20722bd3"},"schema_version":"1.0"},"canonical_sha256":"d368c1da6196fe7d6e0e2a43ca4e755fb981f6e2c614dc1f2483d5a3a36077b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:28.378338Z","signature_b64":"L5V4c/faMHyfUmYo1fujdkLDzzMYPEhTiQE+rqjAlH/6dH/uHWG24fVM64Fyk0d8rElu2RKcWoHWLFdrEixKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d368c1da6196fe7d6e0e2a43ca4e755fb981f6e2c614dc1f2483d5a3a36077b2","last_reissued_at":"2026-07-05T07:49:28.377928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:28.377928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.02902","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIKeBbrGe8NrMPNKbhbM8sDswi+gLPIMAvZw/ChhP7HJJLuaa9HAN1VPYPMWlxPDFvxU0hccqmxWqFN9APJiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:54:30.324075Z"},"content_sha256":"711249af6635652a176dd01932a5f73e711231014fb12fc022c7f56631e314d5","schema_version":"1.0","event_id":"sha256:711249af6635652a176dd01932a5f73e711231014fb12fc022c7f56631e314d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2NUMDWTBS37H23QOFJB4UTTVL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-Space Planning with Subgoal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Chunlok Lo, Farzane Aminmansour, Gabor Mihucz, Kevin Roice, Martha White, Parham Mohammad Panahi, Scott Jordan","submitted_at":"2022-06-06T20:59:07Z","abstract_excerpt":"This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02902","kind":"arxiv","version":5},"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/2206.02902/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":"2026-07-05T07:49:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iUlT4ctTef/4nHWuaf4XRiGaWS8qD4C8+GyXcyUMxsq6jHDxSYrqDDAu/rCK0MiSxVusqrhPYSOLZmt1+/lPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:54:30.324753Z"},"content_sha256":"478c170383d53b4640c2cbfb644f3a79c3468a8610f0b5a6ab071f57e017efec","schema_version":"1.0","event_id":"sha256:478c170383d53b4640c2cbfb644f3a79c3468a8610f0b5a6ab071f57e017efec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NUMDWTBS37H23QOFJB4UTTVL6/bundle.json","state_url":"https://pith.science/pith/2NUMDWTBS37H23QOFJB4UTTVL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NUMDWTBS37H23QOFJB4UTTVL6/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":"2026-07-09T05:54:30Z","links":{"resolver":"https://pith.science/pith/2NUMDWTBS37H23QOFJB4UTTVL6","bundle":"https://pith.science/pith/2NUMDWTBS37H23QOFJB4UTTVL6/bundle.json","state":"https://pith.science/pith/2NUMDWTBS37H23QOFJB4UTTVL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NUMDWTBS37H23QOFJB4UTTVL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2NUMDWTBS37H23QOFJB4UTTVL6","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":"99a4e47e20f0879c7e33f21c4daab2333b7e85082ec7ef8e272b371f20722bd3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:59:07Z","title_canon_sha256":"348cccfd9cb10937621dda354a43ddb74ad8b96a8ec9ee2f513675820fe9564d"},"schema_version":"1.0","source":{"id":"2206.02902","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02902","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02902v5","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02902","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_12","alias_value":"2NUMDWTBS37H","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_16","alias_value":"2NUMDWTBS37H23QO","created_at":"2026-07-05T07:49:28Z"},{"alias_kind":"pith_short_8","alias_value":"2NUMDWTB","created_at":"2026-07-05T07:49:28Z"}],"graph_snapshots":[{"event_id":"sha256:478c170383d53b4640c2cbfb644f3a79c3468a8610f0b5a6ab071f57e017efec","target":"graph","created_at":"2026-07-05T07:49:28Z","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/2206.02902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning ","authors_text":"Adam White, Chunlok Lo, Farzane Aminmansour, Gabor Mihucz, Kevin Roice, Martha White, Parham Mohammad Panahi, Scott Jordan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:59:07Z","title":"Goal-Space Planning with Subgoal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02902","kind":"arxiv","version":5},"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":"sha256:711249af6635652a176dd01932a5f73e711231014fb12fc022c7f56631e314d5","target":"record","created_at":"2026-07-05T07:49:28Z","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":"99a4e47e20f0879c7e33f21c4daab2333b7e85082ec7ef8e272b371f20722bd3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:59:07Z","title_canon_sha256":"348cccfd9cb10937621dda354a43ddb74ad8b96a8ec9ee2f513675820fe9564d"},"schema_version":"1.0","source":{"id":"2206.02902","kind":"arxiv","version":5}},"canonical_sha256":"d368c1da6196fe7d6e0e2a43ca4e755fb981f6e2c614dc1f2483d5a3a36077b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d368c1da6196fe7d6e0e2a43ca4e755fb981f6e2c614dc1f2483d5a3a36077b2","first_computed_at":"2026-07-05T07:49:28.377928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:28.377928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L5V4c/faMHyfUmYo1fujdkLDzzMYPEhTiQE+rqjAlH/6dH/uHWG24fVM64Fyk0d8rElu2RKcWoHWLFdrEixKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:28.378338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02902","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:711249af6635652a176dd01932a5f73e711231014fb12fc022c7f56631e314d5","sha256:478c170383d53b4640c2cbfb644f3a79c3468a8610f0b5a6ab071f57e017efec"],"state_sha256":"8c275b034cb10aa50a4f1f736814336809029d3a8ee4ea7497c6841859885206"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SHXuxbaFA1KcdJkzUEQJL2qJiG363+oNoEzyxkHhZXIS0YaCg0zTpMNV46I7c90hgklL2ZBVMRLhdz183YNvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:54:30.328750Z","bundle_sha256":"ae3114e99a5939b55da24fe8561b853f7effe957ed305da7113b2b54381dc266"}}