{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DCIZOW45KISHK7ZMNNEAIP4PF","short_pith_number":"pith:7DCIZOW4","schema_version":"1.0","canonical_sha256":"f8c48cbadcea9123abf9635a4021fc796078248f5ec50690ad1e9ad2ba37afd7","source":{"kind":"arxiv","id":"2501.18784","version":5},"attestation_state":"computed","paper":{"title":"Successor-Generator Planning with LLM-generated Heuristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Shleyfman, Alexander Tuisov, Yonatan Vernik","submitted_at":"2025-01-30T22:21:12Z","abstract_excerpt":"Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning. This work revisits that paradigm in light of recent advances in large language models (LLMs), which enable the automatic synthesis of heuristics directly from problem definitions -- bypassing the need for handcrafted domain knowledge. We present a method that employs LLMs to generate problem-specific heuristic functions from planning tasks specified through successor generators, goal tests, and initial states written in "},"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":"2501.18784","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T22:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"0699d183bcfb2ada2e52210e6489bfe742848030db2aec657edc9d9faff9822b","abstract_canon_sha256":"03be2d715f1c26b95a9f615e207ff8f638199af6b6942de71404ffc3b16515ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:19:34.985032Z","signature_b64":"kN9CSVvRdtiDzlbXkcBFClcFOCIHTQeAnoEuckHVdJS4HgrT9JN9LFsShEZXkxv/BQl+HFvesGPEegT6sK0UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c48cbadcea9123abf9635a4021fc796078248f5ec50690ad1e9ad2ba37afd7","last_reissued_at":"2026-07-09T01:19:34.984566Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:19:34.984566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Successor-Generator Planning with LLM-generated Heuristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Shleyfman, Alexander Tuisov, Yonatan Vernik","submitted_at":"2025-01-30T22:21:12Z","abstract_excerpt":"Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning. This work revisits that paradigm in light of recent advances in large language models (LLMs), which enable the automatic synthesis of heuristics directly from problem definitions -- bypassing the need for handcrafted domain knowledge. We present a method that employs LLMs to generate problem-specific heuristic functions from planning tasks specified through successor generators, goal tests, and initial states written in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18784","kind":"arxiv","version":5},"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/2501.18784/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":"2501.18784","created_at":"2026-07-09T01:19:34.984619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18784v5","created_at":"2026-07-09T01:19:34.984619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18784","created_at":"2026-07-09T01:19:34.984619+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DCIZOW45KIS","created_at":"2026-07-09T01:19:34.984619+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DCIZOW45KISHK7Z","created_at":"2026-07-09T01:19:34.984619+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DCIZOW4","created_at":"2026-07-09T01:19:34.984619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07707","citing_title":"Hierarchical Task Network Planning with LLM-Generated Heuristics","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29649","citing_title":"LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21902","citing_title":"Planning in the LLM Era: Building for Reliability and Efficiency","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07707","citing_title":"Hierarchical Task Network Planning with LLM-Generated Heuristics","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF","json":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF.json","graph_json":"https://pith.science/api/pith-number/7DCIZOW45KISHK7ZMNNEAIP4PF/graph.json","events_json":"https://pith.science/api/pith-number/7DCIZOW45KISHK7ZMNNEAIP4PF/events.json","paper":"https://pith.science/paper/7DCIZOW4"},"agent_actions":{"view_html":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF","download_json":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF.json","view_paper":"https://pith.science/paper/7DCIZOW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18784&json=true","fetch_graph":"https://pith.science/api/pith-number/7DCIZOW45KISHK7ZMNNEAIP4PF/graph.json","fetch_events":"https://pith.science/api/pith-number/7DCIZOW45KISHK7ZMNNEAIP4PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF/action/storage_attestation","attest_author":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF/action/author_attestation","sign_citation":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF/action/citation_signature","submit_replication":"https://pith.science/pith/7DCIZOW45KISHK7ZMNNEAIP4PF/action/replication_record"}},"created_at":"2026-07-09T01:19:34.984619+00:00","updated_at":"2026-07-09T01:19:34.984619+00:00"}