{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UIBVPGFPPRTX7HTE6YZH2JRGAY","short_pith_number":"pith:UIBVPGFP","schema_version":"1.0","canonical_sha256":"a2035798af7c677f9e64f6327d2626062adffe15b9def8e5c36d80e441483453","source":{"kind":"arxiv","id":"2412.05366","version":2},"attestation_state":"computed","paper":{"title":"ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Binhua Li, Chen Zhi, Fei Huang, Shuiguang Deng, Yongbin Li, Yue Zhang, Yunkun Wang, Zhen Qin","submitted_at":"2024-12-06T19:00:15Z","abstract_excerpt":"Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhaustively retrain LLMs with new API knowledge. This limitation hampers LLMs from solving programming problems which require newly introduced or privately maintained libraries. Inspired by exploratory programming paradigm in human behavior, we propose ExploraCoder, a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by (1) planning a complex problem into several API invocation subta"},"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":"2412.05366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T19:00:15Z","cross_cats_sorted":[],"title_canon_sha256":"abce6779636074091e610671d35df14ab15e6e88d8b55e565f49108ca9187b93","abstract_canon_sha256":"080cd9662630bdb0170c987180090854c0534eda7aa0ec7c3f8767574694718a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:09.969997Z","signature_b64":"7piOAJ8Ed4+D9nG+Ffx9nYow+ou6WPG42GSk0Sh5blX2mqI2/5L+eaGFyjWJi7069Qll5C8sIucrJzx/adVlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2035798af7c677f9e64f6327d2626062adffe15b9def8e5c36d80e441483453","last_reissued_at":"2026-07-05T11:24:09.969445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:09.969445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Binhua Li, Chen Zhi, Fei Huang, Shuiguang Deng, Yongbin Li, Yue Zhang, Yunkun Wang, Zhen Qin","submitted_at":"2024-12-06T19:00:15Z","abstract_excerpt":"Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhaustively retrain LLMs with new API knowledge. This limitation hampers LLMs from solving programming problems which require newly introduced or privately maintained libraries. Inspired by exploratory programming paradigm in human behavior, we propose ExploraCoder, a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by (1) planning a complex problem into several API invocation subta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05366","kind":"arxiv","version":2},"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/2412.05366/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":"2412.05366","created_at":"2026-07-05T11:24:09.969508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05366v2","created_at":"2026-07-05T11:24:09.969508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05366","created_at":"2026-07-05T11:24:09.969508+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIBVPGFPPRTX","created_at":"2026-07-05T11:24:09.969508+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIBVPGFPPRTX7HTE","created_at":"2026-07-05T11:24:09.969508+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIBVPGFP","created_at":"2026-07-05T11:24:09.969508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY","json":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY.json","graph_json":"https://pith.science/api/pith-number/UIBVPGFPPRTX7HTE6YZH2JRGAY/graph.json","events_json":"https://pith.science/api/pith-number/UIBVPGFPPRTX7HTE6YZH2JRGAY/events.json","paper":"https://pith.science/paper/UIBVPGFP"},"agent_actions":{"view_html":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY","download_json":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY.json","view_paper":"https://pith.science/paper/UIBVPGFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05366&json=true","fetch_graph":"https://pith.science/api/pith-number/UIBVPGFPPRTX7HTE6YZH2JRGAY/graph.json","fetch_events":"https://pith.science/api/pith-number/UIBVPGFPPRTX7HTE6YZH2JRGAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY/action/storage_attestation","attest_author":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY/action/author_attestation","sign_citation":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY/action/citation_signature","submit_replication":"https://pith.science/pith/UIBVPGFPPRTX7HTE6YZH2JRGAY/action/replication_record"}},"created_at":"2026-07-05T11:24:09.969508+00:00","updated_at":"2026-07-05T11:24:09.969508+00:00"}