{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GRKH4CGP5VC6YE3TL5DYWXK5UM","short_pith_number":"pith:GRKH4CGP","schema_version":"1.0","canonical_sha256":"34547e08cfed45ec13735f478b5d5da312dcdb06f4db23d3c0d180e81bbd9a80","source":{"kind":"arxiv","id":"2505.10749","version":1},"attestation_state":"computed","paper":{"title":"Code-Driven Planning in Grid Worlds with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ashwath Vaithinathan Aravindan, Mayank Kejriwal, Zhisheng Tang","submitted_at":"2025-05-15T23:23:31Z","abstract_excerpt":"We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis, where the LLM outputs executable programs that map environment states to action sequences. Our proposed architecture incorporates several prompting strategies, including direct code generation, pseudocode-conditioned refinement, and curriculum-based prompting, but also includes an itera"},"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":"2505.10749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-15T23:23:31Z","cross_cats_sorted":[],"title_canon_sha256":"0176d73341fa9b9066ca371d8cb89b5b7a8243dc45c1ab22a94d35025c69eab4","abstract_canon_sha256":"51b19eb0bdc83cbb726c402045b4a2721cf260b0e9fa1401c369398657321d38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:04.868959Z","signature_b64":"yXv8cmLYjN2EP9vDTDtx9rWNJimLN5VqS93Upau29XMZWHgzGOww9dzcDfT0kreoC9NQ8CKhaWTKNYM2rdT5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34547e08cfed45ec13735f478b5d5da312dcdb06f4db23d3c0d180e81bbd9a80","last_reissued_at":"2026-07-05T11:04:04.868486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:04.868486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-Driven Planning in Grid Worlds with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ashwath Vaithinathan Aravindan, Mayank Kejriwal, Zhisheng Tang","submitted_at":"2025-05-15T23:23:31Z","abstract_excerpt":"We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis, where the LLM outputs executable programs that map environment states to action sequences. Our proposed architecture incorporates several prompting strategies, including direct code generation, pseudocode-conditioned refinement, and curriculum-based prompting, but also includes an itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10749","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/2505.10749/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":"2505.10749","created_at":"2026-07-05T11:04:04.868544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10749v1","created_at":"2026-07-05T11:04:04.868544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10749","created_at":"2026-07-05T11:04:04.868544+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRKH4CGP5VC6","created_at":"2026-07-05T11:04:04.868544+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRKH4CGP5VC6YE3T","created_at":"2026-07-05T11:04:04.868544+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRKH4CGP","created_at":"2026-07-05T11:04:04.868544+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/GRKH4CGP5VC6YE3TL5DYWXK5UM","json":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM.json","graph_json":"https://pith.science/api/pith-number/GRKH4CGP5VC6YE3TL5DYWXK5UM/graph.json","events_json":"https://pith.science/api/pith-number/GRKH4CGP5VC6YE3TL5DYWXK5UM/events.json","paper":"https://pith.science/paper/GRKH4CGP"},"agent_actions":{"view_html":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM","download_json":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM.json","view_paper":"https://pith.science/paper/GRKH4CGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10749&json=true","fetch_graph":"https://pith.science/api/pith-number/GRKH4CGP5VC6YE3TL5DYWXK5UM/graph.json","fetch_events":"https://pith.science/api/pith-number/GRKH4CGP5VC6YE3TL5DYWXK5UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM/action/storage_attestation","attest_author":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM/action/author_attestation","sign_citation":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM/action/citation_signature","submit_replication":"https://pith.science/pith/GRKH4CGP5VC6YE3TL5DYWXK5UM/action/replication_record"}},"created_at":"2026-07-05T11:04:04.868544+00:00","updated_at":"2026-07-05T11:04:04.868544+00:00"}