{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KRIBY24IV5QHEW7L4JU4LDZEYG","short_pith_number":"pith:KRIBY24I","schema_version":"1.0","canonical_sha256":"54501c6b88af60725bebe269c58f24c190f09812ddc1b07d1c1f9f497820d483","source":{"kind":"arxiv","id":"2504.21276","version":1},"attestation_state":"computed","paper":{"title":"Assessing LLM code generation quality through path planning tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Mary L. Cummings, Meng-Wen Su, Wanyi Chen","submitted_at":"2025-04-30T03:11:54Z","abstract_excerpt":"As LLM-generated code grows in popularity, more evaluation is needed to assess the risks of using such tools, especially for safety-critical applications such as path planning. Existing coding benchmarks are insufficient as they do not reflect the context and complexity of safety-critical applications. To this end, we assessed six LLMs' abilities to generate the code for three different path-planning algorithms and tested them on three maps of various difficulties. Our results suggest that LLM-generated code presents serious hazards for path planning applications and should not be applied in s"},"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":"2504.21276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-30T03:11:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54505b3921f3f3c239b75c72fc71824739a29c3b55832cee74cbf51a4447903c","abstract_canon_sha256":"b9986910a018f9d22f8ede01991f0af121a4543249c0baff500207ff4632b594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:21.300261Z","signature_b64":"rZP+wpc81zrRDZj68UfZ8IGa8uC4lxTj2dvnu503MwmtIPiC9Lt/0my58uHhE1NOYjEQd0LfIVkcfqZD47TmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54501c6b88af60725bebe269c58f24c190f09812ddc1b07d1c1f9f497820d483","last_reissued_at":"2026-07-05T10:56:21.299818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:21.299818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing LLM code generation quality through path planning tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Mary L. Cummings, Meng-Wen Su, Wanyi Chen","submitted_at":"2025-04-30T03:11:54Z","abstract_excerpt":"As LLM-generated code grows in popularity, more evaluation is needed to assess the risks of using such tools, especially for safety-critical applications such as path planning. Existing coding benchmarks are insufficient as they do not reflect the context and complexity of safety-critical applications. To this end, we assessed six LLMs' abilities to generate the code for three different path-planning algorithms and tested them on three maps of various difficulties. Our results suggest that LLM-generated code presents serious hazards for path planning applications and should not be applied in s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21276","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/2504.21276/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":"2504.21276","created_at":"2026-07-05T10:56:21.299879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21276v1","created_at":"2026-07-05T10:56:21.299879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21276","created_at":"2026-07-05T10:56:21.299879+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRIBY24IV5QH","created_at":"2026-07-05T10:56:21.299879+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRIBY24IV5QHEW7L","created_at":"2026-07-05T10:56:21.299879+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRIBY24I","created_at":"2026-07-05T10:56:21.299879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG","json":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG.json","graph_json":"https://pith.science/api/pith-number/KRIBY24IV5QHEW7L4JU4LDZEYG/graph.json","events_json":"https://pith.science/api/pith-number/KRIBY24IV5QHEW7L4JU4LDZEYG/events.json","paper":"https://pith.science/paper/KRIBY24I"},"agent_actions":{"view_html":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG","download_json":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG.json","view_paper":"https://pith.science/paper/KRIBY24I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21276&json=true","fetch_graph":"https://pith.science/api/pith-number/KRIBY24IV5QHEW7L4JU4LDZEYG/graph.json","fetch_events":"https://pith.science/api/pith-number/KRIBY24IV5QHEW7L4JU4LDZEYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG/action/storage_attestation","attest_author":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG/action/author_attestation","sign_citation":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG/action/citation_signature","submit_replication":"https://pith.science/pith/KRIBY24IV5QHEW7L4JU4LDZEYG/action/replication_record"}},"created_at":"2026-07-05T10:56:21.299879+00:00","updated_at":"2026-07-05T10:56:21.299879+00:00"}