{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6T3RMBLUIVP4NPPAODQBHNOJCA","short_pith_number":"pith:6T3RMBLU","canonical_record":{"source":{"id":"2203.00669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-03-01T18:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"66e5a5a3a2aab57a34e868a17cba90b9054b182ed0c419777134f0361236ba8a","abstract_canon_sha256":"dde19b121f5780415d6130a9bf8330f88b3f8e97bdc8f4daf8aac3e525b55f4e"},"schema_version":"1.0"},"canonical_sha256":"f4f7160574455fc6bde070e013b5c9100129b3595efdacf4d9eab620569f1bed","source":{"kind":"arxiv","id":"2203.00669","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00669","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00669v2","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00669","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"6T3RMBLUIVP4","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"6T3RMBLUIVP4NPPA","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"6T3RMBLU","created_at":"2026-07-05T05:01:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6T3RMBLUIVP4NPPAODQBHNOJCA","target":"record","payload":{"canonical_record":{"source":{"id":"2203.00669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-03-01T18:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"66e5a5a3a2aab57a34e868a17cba90b9054b182ed0c419777134f0361236ba8a","abstract_canon_sha256":"dde19b121f5780415d6130a9bf8330f88b3f8e97bdc8f4daf8aac3e525b55f4e"},"schema_version":"1.0"},"canonical_sha256":"f4f7160574455fc6bde070e013b5c9100129b3595efdacf4d9eab620569f1bed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:50.786400Z","signature_b64":"ldBoVyxeZzWZBc610lykgXcdaA65Aipnt8cJb4r72VGo3Uj1uu9DYjUCYrUb4bALrlQgQ+ttP+t+6m8RZSEPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4f7160574455fc6bde070e013b5c9100129b3595efdacf4d9eab620569f1bed","last_reissued_at":"2026-07-05T05:01:50.785976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:50.785976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.00669","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":"2026-07-05T05:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMmM9DuO/mN1ndG9oaa5tSEVh/11nWX+rTOQO7eAWMuZidNwq2OiV8eBZnXQFuRzKUsocQ4U3K4c63OG7rW8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:33:37.773260Z"},"content_sha256":"6a164d3546cbaad77872413c3f2f1e33911731ee8cb9eaa7b0f8af4286a847dd","schema_version":"1.0","event_id":"sha256:6a164d3546cbaad77872413c3f2f1e33911731ee8cb9eaa7b0f8af4286a847dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6T3RMBLUIVP4NPPAODQBHNOJCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning with AI Planning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Don Joven Agravante, Geraud Nangue Tasse, Junkyu Lee, Miao Liu, Michael Katz, Shirin Sohrabi, Tim Klinger","submitted_at":"2022-03-01T18:38:41Z","abstract_excerpt":"Two common approaches to sequential decision-making are AI planning (AIP) and reinforcement learning (RL). Each has strengths and weaknesses. AIP is interpretable, easy to integrate with symbolic knowledge, and often efficient, but requires an up-front logical domain specification and is sensitive to noise; RL only requires specification of rewards and is robust to noise but is sample inefficient and not easily supplied with external knowledge. We propose an integrative approach that combines high-level planning with RL, retaining interpretability, transfer, and efficiency, while allowing for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00669","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/2203.00669/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":"2026-07-05T05:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hs88VcxALAKAjxYK8pPmjgYju1xkZbV4PZCF4GGNpUqtlgJiR4LGQkvYwQicMguI57mh00VUSvd3WUfPzy7/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:33:37.773638Z"},"content_sha256":"55deeca631b6776a98ca9d8b7a24773d29530fb883c63275be791593c79fcf14","schema_version":"1.0","event_id":"sha256:55deeca631b6776a98ca9d8b7a24773d29530fb883c63275be791593c79fcf14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/bundle.json","state_url":"https://pith.science/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/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":"2026-08-03T18:33:37Z","links":{"resolver":"https://pith.science/pith/6T3RMBLUIVP4NPPAODQBHNOJCA","bundle":"https://pith.science/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/bundle.json","state":"https://pith.science/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6T3RMBLUIVP4NPPAODQBHNOJCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6T3RMBLUIVP4NPPAODQBHNOJCA","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":"dde19b121f5780415d6130a9bf8330f88b3f8e97bdc8f4daf8aac3e525b55f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-03-01T18:38:41Z","title_canon_sha256":"66e5a5a3a2aab57a34e868a17cba90b9054b182ed0c419777134f0361236ba8a"},"schema_version":"1.0","source":{"id":"2203.00669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00669","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00669v2","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00669","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"6T3RMBLUIVP4","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"6T3RMBLUIVP4NPPA","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"6T3RMBLU","created_at":"2026-07-05T05:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:55deeca631b6776a98ca9d8b7a24773d29530fb883c63275be791593c79fcf14","target":"graph","created_at":"2026-07-05T05:01:50Z","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/2203.00669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two common approaches to sequential decision-making are AI planning (AIP) and reinforcement learning (RL). Each has strengths and weaknesses. AIP is interpretable, easy to integrate with symbolic knowledge, and often efficient, but requires an up-front logical domain specification and is sensitive to noise; RL only requires specification of rewards and is robust to noise but is sample inefficient and not easily supplied with external knowledge. We propose an integrative approach that combines high-level planning with RL, retaining interpretability, transfer, and efficiency, while allowing for ","authors_text":"Don Joven Agravante, Geraud Nangue Tasse, Junkyu Lee, Miao Liu, Michael Katz, Shirin Sohrabi, Tim Klinger","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-03-01T18:38:41Z","title":"Hierarchical Reinforcement Learning with AI Planning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00669","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":"sha256:6a164d3546cbaad77872413c3f2f1e33911731ee8cb9eaa7b0f8af4286a847dd","target":"record","created_at":"2026-07-05T05:01:50Z","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":"dde19b121f5780415d6130a9bf8330f88b3f8e97bdc8f4daf8aac3e525b55f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-03-01T18:38:41Z","title_canon_sha256":"66e5a5a3a2aab57a34e868a17cba90b9054b182ed0c419777134f0361236ba8a"},"schema_version":"1.0","source":{"id":"2203.00669","kind":"arxiv","version":2}},"canonical_sha256":"f4f7160574455fc6bde070e013b5c9100129b3595efdacf4d9eab620569f1bed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4f7160574455fc6bde070e013b5c9100129b3595efdacf4d9eab620569f1bed","first_computed_at":"2026-07-05T05:01:50.785976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:50.785976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldBoVyxeZzWZBc610lykgXcdaA65Aipnt8cJb4r72VGo3Uj1uu9DYjUCYrUb4bALrlQgQ+ttP+t+6m8RZSEPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:50.786400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a164d3546cbaad77872413c3f2f1e33911731ee8cb9eaa7b0f8af4286a847dd","sha256:55deeca631b6776a98ca9d8b7a24773d29530fb883c63275be791593c79fcf14"],"state_sha256":"53466caa052f5a777eacae6e108fc41c3feb26ac943c8d21d4f2c5d392e34a2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Wg1F7fj9ByPJp9aPkvVcBaqzCfEcv8omg52K8rJeVjjyirfLmo/acHsza0KvxWTnH0n+4TbguM4Ab3sZ+kBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:33:37.776178Z","bundle_sha256":"0bfce6e579d8d5d399ed857e2ecdc35653469426db1d0c1c315c6aff24b61c7f"}}