{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KOSAYAKR26NYGZB3PZPBVDBQW5","short_pith_number":"pith:KOSAYAKR","canonical_record":{"source":{"id":"2304.08349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-17T15:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5557a7a9ed512d72590263e2dba0fd30448efff003670d06dc0301e7f424f113","abstract_canon_sha256":"38ab7f53a7236573bc39ae651b1954d25149ccb920f76f6b5740b904d797ce0e"},"schema_version":"1.0"},"canonical_sha256":"53a40c0151d79b83643b7e5e1a8c30b77735fb7656fa716f834fed58e8a315d1","source":{"kind":"arxiv","id":"2304.08349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08349","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08349v2","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08349","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"KOSAYAKR26NY","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"KOSAYAKR26NYGZB3","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"KOSAYAKR","created_at":"2026-07-05T06:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KOSAYAKR26NYGZB3PZPBVDBQW5","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-17T15:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5557a7a9ed512d72590263e2dba0fd30448efff003670d06dc0301e7f424f113","abstract_canon_sha256":"38ab7f53a7236573bc39ae651b1954d25149ccb920f76f6b5740b904d797ce0e"},"schema_version":"1.0"},"canonical_sha256":"53a40c0151d79b83643b7e5e1a8c30b77735fb7656fa716f834fed58e8a315d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:44.777440Z","signature_b64":"ON5z09zAGB/dILn8OjSnuwlgFGIm9nY6VoCBp+yDZSUm2Xi1eGY1uE5laqw0J+4CcU2Gs4tp2LR7hc05flL2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53a40c0151d79b83643b7e5e1a8c30b77735fb7656fa716f834fed58e8a315d1","last_reissued_at":"2026-07-05T06:30:44.776925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:44.776925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08349","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":"2026-07-05T06:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QD3LiCDYpAiLWZTEeP2XlU4VhsBwUgvIuC27mt40gbrNiI4H7zsaqogz5lwDy5dGzPYKi1he1eoVeHTYUEu8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:50.808493Z"},"content_sha256":"7a66ca70253b431b82069ba0e932795d0ba07b989d968350a7c5760c2d7718b9","schema_version":"1.0","event_id":"sha256:7a66ca70253b431b82069ba0e932795d0ba07b989d968350a7c5760c2d7718b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KOSAYAKR26NYGZB3PZPBVDBQW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Luc De Raedt, Rishi Hazra","submitted_at":"2023-04-17T15:11:40Z","abstract_excerpt":"Despite numerous successes in Deep Reinforcement Learning (DRL), the learned policies are not interpretable. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with structural changes in its environment (such as increasing the number of objects). Relational Reinforcement Learning, on the other hand, inherits the relational representations from symbolic planning to learn reusable policies. However, it has so far been unable to scale up and exploit the power of deep neural networks. We propose Deep Explainable Relational Reinforcement Learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08349","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/2304.08349/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":"2026-07-05T06:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ei8/vyG16RmgfNnZYA3PF9W03ivsuYNd2+yg/yvrA+hHlngIQYg6EKbO5s55aMERdotPVYFX/zToX42fk4QGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:50.809066Z"},"content_sha256":"5580088402f65812ae46815b918ef38252cd14affa2cf2711d0b8d0685b267ce","schema_version":"1.0","event_id":"sha256:5580088402f65812ae46815b918ef38252cd14affa2cf2711d0b8d0685b267ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/bundle.json","state_url":"https://pith.science/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/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":"2026-08-04T19:05:50Z","links":{"resolver":"https://pith.science/pith/KOSAYAKR26NYGZB3PZPBVDBQW5","bundle":"https://pith.science/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/bundle.json","state":"https://pith.science/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOSAYAKR26NYGZB3PZPBVDBQW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KOSAYAKR26NYGZB3PZPBVDBQW5","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":"38ab7f53a7236573bc39ae651b1954d25149ccb920f76f6b5740b904d797ce0e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-17T15:11:40Z","title_canon_sha256":"5557a7a9ed512d72590263e2dba0fd30448efff003670d06dc0301e7f424f113"},"schema_version":"1.0","source":{"id":"2304.08349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08349","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08349v2","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08349","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"KOSAYAKR26NY","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"KOSAYAKR26NYGZB3","created_at":"2026-07-05T06:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"KOSAYAKR","created_at":"2026-07-05T06:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:5580088402f65812ae46815b918ef38252cd14affa2cf2711d0b8d0685b267ce","target":"graph","created_at":"2026-07-05T06:30:44Z","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/2304.08349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite numerous successes in Deep Reinforcement Learning (DRL), the learned policies are not interpretable. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with structural changes in its environment (such as increasing the number of objects). Relational Reinforcement Learning, on the other hand, inherits the relational representations from symbolic planning to learn reusable policies. However, it has so far been unable to scale up and exploit the power of deep neural networks. We propose Deep Explainable Relational Reinforcement Learning","authors_text":"Luc De Raedt, Rishi Hazra","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-17T15:11:40Z","title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08349","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":"sha256:7a66ca70253b431b82069ba0e932795d0ba07b989d968350a7c5760c2d7718b9","target":"record","created_at":"2026-07-05T06:30:44Z","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":"38ab7f53a7236573bc39ae651b1954d25149ccb920f76f6b5740b904d797ce0e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-17T15:11:40Z","title_canon_sha256":"5557a7a9ed512d72590263e2dba0fd30448efff003670d06dc0301e7f424f113"},"schema_version":"1.0","source":{"id":"2304.08349","kind":"arxiv","version":2}},"canonical_sha256":"53a40c0151d79b83643b7e5e1a8c30b77735fb7656fa716f834fed58e8a315d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53a40c0151d79b83643b7e5e1a8c30b77735fb7656fa716f834fed58e8a315d1","first_computed_at":"2026-07-05T06:30:44.776925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:44.776925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ON5z09zAGB/dILn8OjSnuwlgFGIm9nY6VoCBp+yDZSUm2Xi1eGY1uE5laqw0J+4CcU2Gs4tp2LR7hc05flL2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:44.777440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a66ca70253b431b82069ba0e932795d0ba07b989d968350a7c5760c2d7718b9","sha256:5580088402f65812ae46815b918ef38252cd14affa2cf2711d0b8d0685b267ce"],"state_sha256":"7c9946f2fa7f7c58ce0c536032b58a73ade45da63e633499e9d0b87fe3c750eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yxz25EAsvjUA08BcRY4CQjPqzP7gfJTNRC4TWvMLpn7nxP8MAlQWnIJNyCcXlXflPWJOTAqtsBq+BKi0sFy1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:05:50.812573Z","bundle_sha256":"5749257df99ee310aeb806ec1d87be2b6ee08f015a8948d02dbe88dec17f92d8"}}