{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QMTNBSWRTE3TPGK56RLPWJIM2C","short_pith_number":"pith:QMTNBSWR","schema_version":"1.0","canonical_sha256":"8326d0cad1993737995df456fb250cd0b9a9743b531865cf2483e39a8310267a","source":{"kind":"arxiv","id":"2607.22898","version":1},"attestation_state":"computed","paper":{"title":"AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Jie \"JW\" Wu","submitted_at":"2026-07-24T20:22:59Z","abstract_excerpt":"Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts leave input formats, error handling, or design decisions unspecified, LLMs fill these gaps with implicit assumptions that shape the generated code's behavior and correctness. Because these assumptions remain hidden, generated code may satisfy tests while violating developer intent. We present AssumptionMiner, a framework that makes implicit assumptions a first-class artifact of LLM-based code generation. In addition to code, AssumptionMiner produ"},"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":"2607.22898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-24T20:22:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"47fd9565dc3398d76abddf4312b09bbef9c642b4efe139b4c81ea0657cfc59a8","abstract_canon_sha256":"b805bda48a28e5a65096355db1d1be451ce8994a28711ac9242edf1437e41126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:00.874250Z","signature_b64":"w49j+aJ5JETr0NccyvuvDpNjP565SVeMnCbvTga8xuJo1e1hU/AG4GyDu0NxYvpGoxqb1dEUHSs0m+wubqHkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8326d0cad1993737995df456fb250cd0b9a9743b531865cf2483e39a8310267a","last_reissued_at":"2026-07-28T00:22:00.873322Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:00.873322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Jie \"JW\" Wu","submitted_at":"2026-07-24T20:22:59Z","abstract_excerpt":"Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts leave input formats, error handling, or design decisions unspecified, LLMs fill these gaps with implicit assumptions that shape the generated code's behavior and correctness. Because these assumptions remain hidden, generated code may satisfy tests while violating developer intent. We present AssumptionMiner, a framework that makes implicit assumptions a first-class artifact of LLM-based code generation. In addition to code, AssumptionMiner produ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22898","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/2607.22898/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":"2607.22898","created_at":"2026-07-28T00:22:00.873797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22898v1","created_at":"2026-07-28T00:22:00.873797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22898","created_at":"2026-07-28T00:22:00.873797+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMTNBSWRTE3T","created_at":"2026-07-28T00:22:00.873797+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMTNBSWRTE3TPGK5","created_at":"2026-07-28T00:22:00.873797+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMTNBSWR","created_at":"2026-07-28T00:22:00.873797+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/QMTNBSWRTE3TPGK56RLPWJIM2C","json":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C.json","graph_json":"https://pith.science/api/pith-number/QMTNBSWRTE3TPGK56RLPWJIM2C/graph.json","events_json":"https://pith.science/api/pith-number/QMTNBSWRTE3TPGK56RLPWJIM2C/events.json","paper":"https://pith.science/paper/QMTNBSWR"},"agent_actions":{"view_html":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C","download_json":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C.json","view_paper":"https://pith.science/paper/QMTNBSWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22898&json=true","fetch_graph":"https://pith.science/api/pith-number/QMTNBSWRTE3TPGK56RLPWJIM2C/graph.json","fetch_events":"https://pith.science/api/pith-number/QMTNBSWRTE3TPGK56RLPWJIM2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C/action/storage_attestation","attest_author":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C/action/author_attestation","sign_citation":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C/action/citation_signature","submit_replication":"https://pith.science/pith/QMTNBSWRTE3TPGK56RLPWJIM2C/action/replication_record"}},"created_at":"2026-07-28T00:22:00.873797+00:00","updated_at":"2026-07-28T00:22:00.873797+00:00"}