{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LT46ADF4GRAPFZUBUXVKTUDHN4","short_pith_number":"pith:LT46ADF4","schema_version":"1.0","canonical_sha256":"5cf9e00cbc3440f2e681a5eaa9d0676f105da1dff103c6eaafd425ddd4c03abc","source":{"kind":"arxiv","id":"2606.04860","version":1},"attestation_state":"computed","paper":{"title":"Learning Empirically Admissible Neural Heuristics for Combinatorial Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Siddharth Sahay","submitted_at":"2026-06-03T13:27:46Z","abstract_excerpt":"Finding optimal solution paths for combinatorial puzzles like the Rubik's Cube, sliding tile puzzles, and Lights Out remains a classical challenge in artificial intelligence. Heuristic search algorithms, such as A* , guarantee path optimality only when using an admissible heuristic-one that never overestimates the true remaining cost-to-go. Deep reinforcement learning (RL) methods like DeepCubeA train deep neural networks to approximate cost-to-go heuristics. However, standard mean-squared error (MSE) training regularly yields overestimations, violating admissibility and compromising solution "},"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":"2606.04860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:27:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5021bceb3f24d4593d030ea54023e0b2ba08a3b397cd4f361a63624bd36232f","abstract_canon_sha256":"1ea2af8ae9b073ee2e9ffb6459bf9320d553d5f9bbc6a46f73a7d304fe87e011"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:32.558832Z","signature_b64":"6hKq1+62phfAy99D5PjeA0qqFktek1Zq524OL17YTTy6/bov3ltRexLjE6uQwIXoyKPMEXsyfbHzPuMHcYBTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cf9e00cbc3440f2e681a5eaa9d0676f105da1dff103c6eaafd425ddd4c03abc","last_reissued_at":"2026-06-04T01:09:32.558366Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:32.558366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Empirically Admissible Neural Heuristics for Combinatorial Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Siddharth Sahay","submitted_at":"2026-06-03T13:27:46Z","abstract_excerpt":"Finding optimal solution paths for combinatorial puzzles like the Rubik's Cube, sliding tile puzzles, and Lights Out remains a classical challenge in artificial intelligence. Heuristic search algorithms, such as A* , guarantee path optimality only when using an admissible heuristic-one that never overestimates the true remaining cost-to-go. Deep reinforcement learning (RL) methods like DeepCubeA train deep neural networks to approximate cost-to-go heuristics. However, standard mean-squared error (MSE) training regularly yields overestimations, violating admissibility and compromising solution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04860","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/2606.04860/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":"2606.04860","created_at":"2026-06-04T01:09:32.558431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04860v1","created_at":"2026-06-04T01:09:32.558431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04860","created_at":"2026-06-04T01:09:32.558431+00:00"},{"alias_kind":"pith_short_12","alias_value":"LT46ADF4GRAP","created_at":"2026-06-04T01:09:32.558431+00:00"},{"alias_kind":"pith_short_16","alias_value":"LT46ADF4GRAPFZUB","created_at":"2026-06-04T01:09:32.558431+00:00"},{"alias_kind":"pith_short_8","alias_value":"LT46ADF4","created_at":"2026-06-04T01:09:32.558431+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/LT46ADF4GRAPFZUBUXVKTUDHN4","json":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4.json","graph_json":"https://pith.science/api/pith-number/LT46ADF4GRAPFZUBUXVKTUDHN4/graph.json","events_json":"https://pith.science/api/pith-number/LT46ADF4GRAPFZUBUXVKTUDHN4/events.json","paper":"https://pith.science/paper/LT46ADF4"},"agent_actions":{"view_html":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4","download_json":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4.json","view_paper":"https://pith.science/paper/LT46ADF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04860&json=true","fetch_graph":"https://pith.science/api/pith-number/LT46ADF4GRAPFZUBUXVKTUDHN4/graph.json","fetch_events":"https://pith.science/api/pith-number/LT46ADF4GRAPFZUBUXVKTUDHN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4/action/storage_attestation","attest_author":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4/action/author_attestation","sign_citation":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4/action/citation_signature","submit_replication":"https://pith.science/pith/LT46ADF4GRAPFZUBUXVKTUDHN4/action/replication_record"}},"created_at":"2026-06-04T01:09:32.558431+00:00","updated_at":"2026-06-04T01:09:32.558431+00:00"}