{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5OUXBLIIHFWEVBPUG2M53LEY63","short_pith_number":"pith:5OUXBLII","schema_version":"1.0","canonical_sha256":"eba970ad08396c4a85f43699ddac98f6cac426f2deb8eccb006e5243641a2dec","source":{"kind":"arxiv","id":"2607.18368","version":1},"attestation_state":"computed","paper":{"title":"Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Cochez, Taewoon Kim, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2026-07-20T17:55:00Z","abstract_excerpt":"Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-graph memory in RoomKG, where hidden state and observations are represented as Resource Description Framework (RDF) graphs and memory is augmented with temporal RDF triple annotations. The model combines knowledge-graph encoding of memory contents with value heads for question answering, exploration, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.18368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T17:55:00Z","cross_cats_sorted":[],"title_canon_sha256":"cfe7da1327d9931d3f8d8db7f3f8c6d60a686662ee9e534d4901e7a9e0042065","abstract_canon_sha256":"575b2501ae37e3b565adf1aee7d391b9194d44e1ea60b3b934f0ecd2d804f8e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:43.892153Z","signature_b64":"AvBqV+0HqwDOkaggnEeIOzVd52Vvoq7TTU52Bv7fdw5I8yDIo8feU8vSifKGZLhh4utxg00U/fF5F1bdvd7BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba970ad08396c4a85f43699ddac98f6cac426f2deb8eccb006e5243641a2dec","last_reissued_at":"2026-07-22T00:22:43.891304Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:43.891304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Cochez, Taewoon Kim, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2026-07-20T17:55:00Z","abstract_excerpt":"Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-graph memory in RoomKG, where hidden state and observations are represented as Resource Description Framework (RDF) graphs and memory is augmented with temporal RDF triple annotations. The model combines knowledge-graph encoding of memory contents with value heads for question answering, exploration, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18368","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/2607.18368/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.18368","created_at":"2026-07-22T00:22:43.891748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18368v1","created_at":"2026-07-22T00:22:43.891748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18368","created_at":"2026-07-22T00:22:43.891748+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OUXBLIIHFWE","created_at":"2026-07-22T00:22:43.891748+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OUXBLIIHFWEVBPU","created_at":"2026-07-22T00:22:43.891748+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OUXBLII","created_at":"2026-07-22T00:22:43.891748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63","json":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63.json","graph_json":"https://pith.science/api/pith-number/5OUXBLIIHFWEVBPUG2M53LEY63/graph.json","events_json":"https://pith.science/api/pith-number/5OUXBLIIHFWEVBPUG2M53LEY63/events.json","paper":"https://pith.science/paper/5OUXBLII"},"agent_actions":{"view_html":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63","download_json":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63.json","view_paper":"https://pith.science/paper/5OUXBLII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18368&json=true","fetch_graph":"https://pith.science/api/pith-number/5OUXBLIIHFWEVBPUG2M53LEY63/graph.json","fetch_events":"https://pith.science/api/pith-number/5OUXBLIIHFWEVBPUG2M53LEY63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63/action/storage_attestation","attest_author":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63/action/author_attestation","sign_citation":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63/action/citation_signature","submit_replication":"https://pith.science/pith/5OUXBLIIHFWEVBPUG2M53LEY63/action/replication_record"}},"created_at":"2026-07-22T00:22:43.891748+00:00","updated_at":"2026-07-22T00:22:43.891748+00:00"}