{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:U4XDZQNHXGWF5E3UAMXGFCI2RU","short_pith_number":"pith:U4XDZQNH","canonical_record":{"source":{"id":"1812.11240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"ea122248531d87cca6785fdda3071f95afe8fc2e78b4b8af75b0df29b8eb853c","abstract_canon_sha256":"7715218b4954153bc12ed0b8c5e076ae72349da9eb04156e0dc1a8be89f82e85"},"schema_version":"1.0"},"canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","source":{"kind":"arxiv","id":"1812.11240","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11240","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11240v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11240","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"U4XDZQNHXGWF","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U4XDZQNHXGWF5E3U","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U4XDZQNH","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:U4XDZQNHXGWF5E3UAMXGFCI2RU","target":"record","payload":{"canonical_record":{"source":{"id":"1812.11240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"ea122248531d87cca6785fdda3071f95afe8fc2e78b4b8af75b0df29b8eb853c","abstract_canon_sha256":"7715218b4954153bc12ed0b8c5e076ae72349da9eb04156e0dc1a8be89f82e85"},"schema_version":"1.0"},"canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.235232Z","signature_b64":"X3vJcEr55WA19PaZkwHKi0vz+R08Y7ZJC67O8+Gga+xRnFdgGT8UvnfHq41dO/Qh/Z1FRMbFGTbK09/zwlG/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","last_reissued_at":"2026-05-17T23:54:53.234756Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.234756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.11240","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":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27zmgWb+0HDgAELjnTBbSPO0FB2J6IhGRZ5luPDPZXk8IuQFht/Q1quCPlNr04Ql3vHwkBsUkwrtx0kqPXMJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:44:49.594515Z"},"content_sha256":"754ecb20d2ffa5b77b43ef9d8401f1782b94e3498ab0df4aed57c70c7c35bc7a","schema_version":"1.0","event_id":"sha256:754ecb20d2ffa5b77b43ef9d8401f1782b94e3498ab0df4aed57c70c7c35bc7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:U4XDZQNHXGWF5E3UAMXGFCI2RU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Planning Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miriam Capretz, Norman Tasfi","submitted_at":"2018-12-28T22:37:30Z","abstract_excerpt":"We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly trial-and-error in the environment. DPN learns to efficiently form plans by expanding a single actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11240","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":""},"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":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZdfEqB5y4qtbxN5alug6h+uwLPc+iVn/pfkwSZ62QOnhxi7fey2yYwX/xumIvIWD6o7Oq3mq3WBtGitA6DtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:44:49.595239Z"},"content_sha256":"9d3cbad64f25bd91ef0daaf9e6ffdfd338d2b805d7324d88abf119097cf0e86e","schema_version":"1.0","event_id":"sha256:9d3cbad64f25bd91ef0daaf9e6ffdfd338d2b805d7324d88abf119097cf0e86e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/bundle.json","state_url":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/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":"2026-06-06T06:44:49Z","links":{"resolver":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU","bundle":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/bundle.json","state":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:U4XDZQNHXGWF5E3UAMXGFCI2RU","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":"7715218b4954153bc12ed0b8c5e076ae72349da9eb04156e0dc1a8be89f82e85","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","title_canon_sha256":"ea122248531d87cca6785fdda3071f95afe8fc2e78b4b8af75b0df29b8eb853c"},"schema_version":"1.0","source":{"id":"1812.11240","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11240","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11240v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11240","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"U4XDZQNHXGWF","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U4XDZQNHXGWF5E3U","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U4XDZQNH","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:9d3cbad64f25bd91ef0daaf9e6ffdfd338d2b805d7324d88abf119097cf0e86e","target":"graph","created_at":"2026-05-17T23:54:53Z","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"},"paper":{"abstract_excerpt":"We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly trial-and-error in the environment. DPN learns to efficiently form plans by expanding a single actio","authors_text":"Miriam Capretz, Norman Tasfi","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","title":"Dynamic Planning Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11240","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":"sha256:754ecb20d2ffa5b77b43ef9d8401f1782b94e3498ab0df4aed57c70c7c35bc7a","target":"record","created_at":"2026-05-17T23:54:53Z","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":"7715218b4954153bc12ed0b8c5e076ae72349da9eb04156e0dc1a8be89f82e85","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","title_canon_sha256":"ea122248531d87cca6785fdda3071f95afe8fc2e78b4b8af75b0df29b8eb853c"},"schema_version":"1.0","source":{"id":"1812.11240","kind":"arxiv","version":2}},"canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","first_computed_at":"2026-05-17T23:54:53.234756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:53.234756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X3vJcEr55WA19PaZkwHKi0vz+R08Y7ZJC67O8+Gga+xRnFdgGT8UvnfHq41dO/Qh/Z1FRMbFGTbK09/zwlG/Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:53.235232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.11240","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:754ecb20d2ffa5b77b43ef9d8401f1782b94e3498ab0df4aed57c70c7c35bc7a","sha256:9d3cbad64f25bd91ef0daaf9e6ffdfd338d2b805d7324d88abf119097cf0e86e"],"state_sha256":"03fa969f56af7eb675a1ec8aeb43a1d17e019c02af44d726d7cd574bcaa55ab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2din9KFztQeSJOROliZtjP8raTkIz8PsSvyDlDygAeSVcY0/iukdI6ZEmjKdAhAGrRZOFBZNl1fOj8OdAVojDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:44:49.598810Z","bundle_sha256":"9e67cba923c1cda6fbb554e9a89c93e35c09f4d2030accc17b072b908a559173"}}