{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FJHVKTMOT3SJJ5BU4WDAQLLZ2","short_pith_number":"pith:3FJHVKTM","schema_version":"1.0","canonical_sha256":"d9527aaa6c74f724a7a1a72c30416bceb211ec72e88fdb51d1c472ff413fe1d4","source":{"kind":"arxiv","id":"2607.06636","version":1},"attestation_state":"computed","paper":{"title":"Specification Grounding Drives Test Effectiveness for LLM Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Amin Haeri, Mahdi Ghelichi","submitted_at":"2026-07-07T14:11:00Z","abstract_excerpt":"Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions. A popular fix has the model write its own tests and repair until they pass, but the source of the gain is unclear: does it come from the tests merely existing, or from their grounding in a specification of what the code should do? We isolate this factor. Holding the tester, test budget, and repair loop fixed, we change a single prompt line that controls whether the tester receives the spec as a checklist of rules. The "},"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":"2607.06636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-07T14:11:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"046c964e3bdfe202cda3e6830506ed203e148a571d5ea028aca7ee3065fb206a","abstract_canon_sha256":"e9f50338c5c808dd45326dc194334662c567d50a42a0b088dc5136489005c7b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:21.251508Z","signature_b64":"6v1Vs/d2QdUeS+f+bU8LuM74dOTtg9Qt6/bPTKBTVZTjdlBKtCwl83XHVliSoHc3Nfii2a+Jrx+8LnKfXGzbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9527aaa6c74f724a7a1a72c30416bceb211ec72e88fdb51d1c472ff413fe1d4","last_reissued_at":"2026-07-09T00:19:21.250773Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:21.250773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specification Grounding Drives Test Effectiveness for LLM Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Amin Haeri, Mahdi Ghelichi","submitted_at":"2026-07-07T14:11:00Z","abstract_excerpt":"Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions. A popular fix has the model write its own tests and repair until they pass, but the source of the gain is unclear: does it come from the tests merely existing, or from their grounding in a specification of what the code should do? We isolate this factor. Holding the tester, test budget, and repair loop fixed, we change a single prompt line that controls whether the tester receives the spec as a checklist of rules. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06636","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/2607.06636/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":"2607.06636","created_at":"2026-07-09T00:19:21.250900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06636v1","created_at":"2026-07-09T00:19:21.250900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06636","created_at":"2026-07-09T00:19:21.250900+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FJHVKTMOT3S","created_at":"2026-07-09T00:19:21.250900+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FJHVKTMOT3SJJ5B","created_at":"2026-07-09T00:19:21.250900+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FJHVKTM","created_at":"2026-07-09T00:19:21.250900+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/3FJHVKTMOT3SJJ5BU4WDAQLLZ2","json":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2.json","graph_json":"https://pith.science/api/pith-number/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/graph.json","events_json":"https://pith.science/api/pith-number/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/events.json","paper":"https://pith.science/paper/3FJHVKTM"},"agent_actions":{"view_html":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2","download_json":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2.json","view_paper":"https://pith.science/paper/3FJHVKTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06636&json=true","fetch_graph":"https://pith.science/api/pith-number/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/action/storage_attestation","attest_author":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/action/author_attestation","sign_citation":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/action/citation_signature","submit_replication":"https://pith.science/pith/3FJHVKTMOT3SJJ5BU4WDAQLLZ2/action/replication_record"}},"created_at":"2026-07-09T00:19:21.250900+00:00","updated_at":"2026-07-09T00:19:21.250900+00:00"}