{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F737YMIXEIOY7VIHLW2VXT76KC","short_pith_number":"pith:F737YMIX","canonical_record":{"source":{"id":"2410.11689","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T15:24:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8d64304d95dfdcd11e6d2760682e4a965fe5b7d63d6ff04d58b1447bf620694","abstract_canon_sha256":"b07788a6574e22292fee3232e26301c1b3dfc27e3ec9ca04dae2b2f447693eee"},"schema_version":"1.0"},"canonical_sha256":"2ff7fc3117221d8fd5075db55bcffe508cc4a5f339269f45dc0be9785d4c018f","source":{"kind":"arxiv","id":"2410.11689","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11689","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11689v2","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11689","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"F737YMIXEIOY","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"F737YMIXEIOY7VIH","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"F737YMIX","created_at":"2026-07-05T10:51:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F737YMIXEIOY7VIHLW2VXT76KC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11689","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T15:24:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8d64304d95dfdcd11e6d2760682e4a965fe5b7d63d6ff04d58b1447bf620694","abstract_canon_sha256":"b07788a6574e22292fee3232e26301c1b3dfc27e3ec9ca04dae2b2f447693eee"},"schema_version":"1.0"},"canonical_sha256":"2ff7fc3117221d8fd5075db55bcffe508cc4a5f339269f45dc0be9785d4c018f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:26.539765Z","signature_b64":"KjSNTT/vW2w4fUUZ1GPEo3lJdeOFl8clI6rCkkKEH4iIS4H6bA0xrVBMf8398rMoYf/7jLItsdW1qYodEcK0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ff7fc3117221d8fd5075db55bcffe508cc4a5f339269f45dc0be9785d4c018f","last_reissued_at":"2026-07-05T10:51:26.539275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:26.539275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11689","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":"2026-07-05T10:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6zv9SQtQXfxLEp7YmR3eflvvHaeCBFVUkLh27CUXsd1AvEsu+5uOWIyXE+hUhbbgd8yWhbQjFA+q7bwabJVyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:26:45.655368Z"},"content_sha256":"c87b46ebb19a667b648a936b447e7a5a3b22d10203d72efb85f27e18c463b79a","schema_version":"1.0","event_id":"sha256:c87b46ebb19a667b648a936b447e7a5a3b22d10203d72efb85f27e18c463b79a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F737YMIXEIOY7VIHLW2VXT76KC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Devendra Singh Dhami, Hikaru Shindo, Kristian Kersting, Quentin Delfosse","submitted_at":"2024-10-15T15:24:20Z","abstract_excerpt":"Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11689","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/2410.11689/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":"2026-07-05T10:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1E7IisldP3IqB+Vr58J6HAjAo9GFt2dbbAAxL5UBl7/DS7onw4Y2IScfacU4OchLz/XigI+01zotwIZIv/GBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:26:45.655754Z"},"content_sha256":"085b5ff97542f689aa9e3e8533dadf8d448bc2a7851afa326d33c45ab53cd48f","schema_version":"1.0","event_id":"sha256:085b5ff97542f689aa9e3e8533dadf8d448bc2a7851afa326d33c45ab53cd48f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F737YMIXEIOY7VIHLW2VXT76KC/bundle.json","state_url":"https://pith.science/pith/F737YMIXEIOY7VIHLW2VXT76KC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F737YMIXEIOY7VIHLW2VXT76KC/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":"2026-07-20T15:26:45Z","links":{"resolver":"https://pith.science/pith/F737YMIXEIOY7VIHLW2VXT76KC","bundle":"https://pith.science/pith/F737YMIXEIOY7VIHLW2VXT76KC/bundle.json","state":"https://pith.science/pith/F737YMIXEIOY7VIHLW2VXT76KC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F737YMIXEIOY7VIHLW2VXT76KC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F737YMIXEIOY7VIHLW2VXT76KC","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":"b07788a6574e22292fee3232e26301c1b3dfc27e3ec9ca04dae2b2f447693eee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T15:24:20Z","title_canon_sha256":"c8d64304d95dfdcd11e6d2760682e4a965fe5b7d63d6ff04d58b1447bf620694"},"schema_version":"1.0","source":{"id":"2410.11689","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11689","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11689v2","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11689","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"F737YMIXEIOY","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"F737YMIXEIOY7VIH","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"F737YMIX","created_at":"2026-07-05T10:51:26Z"}],"graph_snapshots":[{"event_id":"sha256:085b5ff97542f689aa9e3e8533dadf8d448bc2a7851afa326d33c45ab53cd48f","target":"graph","created_at":"2026-07-05T10:51:26Z","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/2410.11689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that u","authors_text":"Devendra Singh Dhami, Hikaru Shindo, Kristian Kersting, Quentin Delfosse","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T15:24:20Z","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11689","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:c87b46ebb19a667b648a936b447e7a5a3b22d10203d72efb85f27e18c463b79a","target":"record","created_at":"2026-07-05T10:51:26Z","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":"b07788a6574e22292fee3232e26301c1b3dfc27e3ec9ca04dae2b2f447693eee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T15:24:20Z","title_canon_sha256":"c8d64304d95dfdcd11e6d2760682e4a965fe5b7d63d6ff04d58b1447bf620694"},"schema_version":"1.0","source":{"id":"2410.11689","kind":"arxiv","version":2}},"canonical_sha256":"2ff7fc3117221d8fd5075db55bcffe508cc4a5f339269f45dc0be9785d4c018f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ff7fc3117221d8fd5075db55bcffe508cc4a5f339269f45dc0be9785d4c018f","first_computed_at":"2026-07-05T10:51:26.539275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:26.539275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjSNTT/vW2w4fUUZ1GPEo3lJdeOFl8clI6rCkkKEH4iIS4H6bA0xrVBMf8398rMoYf/7jLItsdW1qYodEcK0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:26.539765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11689","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c87b46ebb19a667b648a936b447e7a5a3b22d10203d72efb85f27e18c463b79a","sha256:085b5ff97542f689aa9e3e8533dadf8d448bc2a7851afa326d33c45ab53cd48f"],"state_sha256":"98b5926f72da93c648860ccb4514f641dd0c2283bed381a8a6d9fe09fcb967ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YFxuEv16kBH1AoDjLYWNbapOPkXt93iAhnuC7Bemd/2/Rk6/aWsi/2G9ciGlxx2BqB+aO+5M9i+Ghc8OqeBjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T15:26:45.658912Z","bundle_sha256":"570a08a5b147e7d8e6bc826896c87928f7e3b48a5f6cca00a18efe1aa2db5360"}}