{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UXYTK7QND33XLWGKQGSRMYJVH5","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":"94cbcdad16f3276bd1f492eb2236ad87fe49172c03a6ded2def41eab6ca85181","cross_cats_sorted":["cs.LG","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-07T15:51:49Z","title_canon_sha256":"3b82140c116d652bff5e36b81006e7188fb37df915fe79b629de440726d0789c"},"schema_version":"1.0","source":{"id":"2501.03888","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03888","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03888v4","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03888","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"UXYTK7QND33X","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"UXYTK7QND33XLWGK","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"UXYTK7QN","created_at":"2026-07-05T10:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:612149c38e25a19d71da242a3ce0bef27bb853cb31469f8a68d8b99b05bc017d","target":"graph","created_at":"2026-07-05T10:53:14Z","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/2501.03888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep reinforcement learning has been shown to be effective, the model's black-box nature presents barriers to direct policy interpretation. To address this problem, we propose a neuro-symbolic approach called neural DNF-MT for end-to-end policy learning. The differentiable nature of the neural DNF-MT model enables the use of deep actor-critic algorithms for training. At the same time, its architecture is designed so that trained models can be directly translated into interpretable policies expressed as standard (bivalent or probabilistic) logic programs. Moreover, additional layers ca","authors_text":"Alessandra Russo, Kexin Gu Baugh, Luke Dickens","cross_cats":["cs.LG","cs.LO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-07T15:51:49Z","title":"Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03888","kind":"arxiv","version":4},"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":"sha256:215c0fb05beb0b25bf61ff1279c3bbac623a7727db4551dbc9aac7385d729965","target":"record","created_at":"2026-07-05T10:53:14Z","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":"94cbcdad16f3276bd1f492eb2236ad87fe49172c03a6ded2def41eab6ca85181","cross_cats_sorted":["cs.LG","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-07T15:51:49Z","title_canon_sha256":"3b82140c116d652bff5e36b81006e7188fb37df915fe79b629de440726d0789c"},"schema_version":"1.0","source":{"id":"2501.03888","kind":"arxiv","version":4}},"canonical_sha256":"a5f1357e0d1ef775d8ca81a51661353f52915eeaa9fa224430a8c1f102dc9c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5f1357e0d1ef775d8ca81a51661353f52915eeaa9fa224430a8c1f102dc9c94","first_computed_at":"2026-07-05T10:53:14.730912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:14.730912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y5ZaWMLjtZNk/OBaZIzFsWPojRg1Ol7XmTRAFA5Gx20V/jqpIaYqTZqWIPl6LK/oKAmoQzdUumvkYcCHgIo0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:14.731432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03888","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:215c0fb05beb0b25bf61ff1279c3bbac623a7727db4551dbc9aac7385d729965","sha256:612149c38e25a19d71da242a3ce0bef27bb853cb31469f8a68d8b99b05bc017d"],"state_sha256":"b1f26335a7c52f116cf068b4d58b7863d22f18c8dba8214e2667be174cfea1dc"}