{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AZLKUFJH2D74MPQZJR2ZWSUDAY","short_pith_number":"pith:AZLKUFJH","canonical_record":{"source":{"id":"2307.14993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e7a4ed5e3fbce61b036f2995739b8cc8acf005a842b0d62f076acaa5ab600af","abstract_canon_sha256":"5c239d4ceed8aeeb6d7ac8b333c3b2388ea712eb8ea2d5d9781048bb59b76c4b"},"schema_version":"1.0"},"canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","source":{"kind":"arxiv","id":"2307.14993","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14993","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14993v2","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14993","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"AZLKUFJH2D74","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"AZLKUFJH2D74MPQZ","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"AZLKUFJH","created_at":"2026-07-05T07:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AZLKUFJH2D74MPQZJR2ZWSUDAY","target":"record","payload":{"canonical_record":{"source":{"id":"2307.14993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e7a4ed5e3fbce61b036f2995739b8cc8acf005a842b0d62f076acaa5ab600af","abstract_canon_sha256":"5c239d4ceed8aeeb6d7ac8b333c3b2388ea712eb8ea2d5d9781048bb59b76c4b"},"schema_version":"1.0"},"canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:46.480366Z","signature_b64":"wds+O0Jz0cwNgu1WnRyXesrPRIdXq773P4+9B5IH2ZVPf9NXiwCfiXSHKm9yr612hNy4Jy/LKsdjReiWc7YwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","last_reissued_at":"2026-07-05T07:05:46.479877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:46.479877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.14993","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":"2026-07-05T07:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2JqfL6ufC47wv/V1CFdX2ktNcreHVUhUhKIwQePc1ztCvWu80TITKit8jGBCUv8lG8ELbUe7BaYAwoEZeH2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:05:58.086611Z"},"content_sha256":"dd0d45f5101f551b0b039cc0003b8fc58e79c74f9f8cebb6264e41c6300050d6","schema_version":"1.0","event_id":"sha256:dd0d45f5101f551b0b039cc0003b8fc58e79c74f9f8cebb6264e41c6300050d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AZLKUFJH2D74MPQZJR2ZWSUDAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thinker: Learning to Plan and Act","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Krueger, Ivan Anokhin, Stephen Chung","submitted_at":"2023-07-27T16:40:14Z","abstract_excerpt":"We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14993","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/2307.14993/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":"2026-07-05T07:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jcS7GzbYVpI4L8mVl3aO0Bj2UAhI5KT8zvbFGllgzYS7pOWwwFVWKtT5YYwfJZPLjKsEKxMXKviGMGJVfxm1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:05:58.087523Z"},"content_sha256":"91b36a478a128becfe2d44c282ff74ed535e565377d51533434f2aed36f66430","schema_version":"1.0","event_id":"sha256:91b36a478a128becfe2d44c282ff74ed535e565377d51533434f2aed36f66430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/bundle.json","state_url":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/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":"2026-08-12T19:05:58Z","links":{"resolver":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY","bundle":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/bundle.json","state":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AZLKUFJH2D74MPQZJR2ZWSUDAY","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":"5c239d4ceed8aeeb6d7ac8b333c3b2388ea712eb8ea2d5d9781048bb59b76c4b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","title_canon_sha256":"7e7a4ed5e3fbce61b036f2995739b8cc8acf005a842b0d62f076acaa5ab600af"},"schema_version":"1.0","source":{"id":"2307.14993","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14993","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14993v2","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14993","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"AZLKUFJH2D74","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"AZLKUFJH2D74MPQZ","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"AZLKUFJH","created_at":"2026-07-05T07:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:91b36a478a128becfe2d44c282ff74ed535e565377d51533434f2aed36f66430","target":"graph","created_at":"2026-07-05T07:05:46Z","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/2307.14993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously","authors_text":"David Krueger, Ivan Anokhin, Stephen Chung","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","title":"Thinker: Learning to Plan and Act"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14993","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:dd0d45f5101f551b0b039cc0003b8fc58e79c74f9f8cebb6264e41c6300050d6","target":"record","created_at":"2026-07-05T07:05:46Z","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":"5c239d4ceed8aeeb6d7ac8b333c3b2388ea712eb8ea2d5d9781048bb59b76c4b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","title_canon_sha256":"7e7a4ed5e3fbce61b036f2995739b8cc8acf005a842b0d62f076acaa5ab600af"},"schema_version":"1.0","source":{"id":"2307.14993","kind":"arxiv","version":2}},"canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","first_computed_at":"2026-07-05T07:05:46.479877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:46.479877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wds+O0Jz0cwNgu1WnRyXesrPRIdXq773P4+9B5IH2ZVPf9NXiwCfiXSHKm9yr612hNy4Jy/LKsdjReiWc7YwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:46.480366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14993","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd0d45f5101f551b0b039cc0003b8fc58e79c74f9f8cebb6264e41c6300050d6","sha256:91b36a478a128becfe2d44c282ff74ed535e565377d51533434f2aed36f66430"],"state_sha256":"dbd0a368a67e647e81b1952b8a5b448a0fa4dcb73dc38d668f0da61585bce324"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ij1WbzTXmC++raQNNpuhFVIUyHG/xabxD9vUOPEjFpUuqIIKK9463nYJSjZ+clOo8SZBQJvO83ouieeOWDULBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:05:58.109485Z","bundle_sha256":"9628bf26bcb85f2da1b4e986a297fc4644b2be20e5504d2d672ac91fa20f4e4b"}}