{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:65LENYMP5AEO5CT7VDCCD3AU2O","short_pith_number":"pith:65LENYMP","schema_version":"1.0","canonical_sha256":"f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd","source":{"kind":"arxiv","id":"2605.14549","version":1},"attestation_state":"computed","paper":{"title":"CSLibPremiseBench: Structure-Guided Premise Retrieval and Label Robustness for Lean 4 Computer-Science Theorems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.","cross_cats":[],"primary_cat":"cs.LO","authors_text":"Junye Ji","submitted_at":"2026-05-14T08:28:57Z","abstract_excerpt":"CSLib is an emerging Lean 4 library for computer-science formalization, but its premise-retrieval behavior is not well represented by broad mathematical theorem-proving benchmarks. We introduce CSLibPremiseBench, a reproducible CSLib-specific benchmark and empirical study for source-visible premise retrieval over Lean 4 theorem and lemma declarations. The benchmark pins CSLib v4.29.0 at commit 0d37cc7fcc985cfc53b155e7eef2453f846c6da2, builds with Lean 4.29.0, and evaluates a strict import/source-order task set with 801 proxy-labelable tasks and 1875 CSLib candidate declarations. The labels are"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2026-05-14T08:28:57Z","cross_cats_sorted":[],"title_canon_sha256":"98424ed4b2b79f191374b94e616f2c70afaa5f93838f0ec7f6066ce090e18c3a","abstract_canon_sha256":"6545c839f80bc4e63467ee1a63f48c05a841200e2089c52f8d1a5cdd0c0def5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.730239Z","signature_b64":"rtFMe4ZUCdCYIpqQTLei/IZvEgRGNnIL6Y5Q5bNLA/8MjOs8wmFhyG0l+a+dQADLRM9O4Otc9vI23msucK21CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd","last_reissued_at":"2026-05-17T23:39:05.729714Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.729714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSLibPremiseBench: Structure-Guided Premise Retrieval and Label Robustness for Lean 4 Computer-Science Theorems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.","cross_cats":[],"primary_cat":"cs.LO","authors_text":"Junye Ji","submitted_at":"2026-05-14T08:28:57Z","abstract_excerpt":"CSLib is an emerging Lean 4 library for computer-science formalization, but its premise-retrieval behavior is not well represented by broad mathematical theorem-proving benchmarks. We introduce CSLibPremiseBench, a reproducible CSLib-specific benchmark and empirical study for source-visible premise retrieval over Lean 4 theorem and lemma declarations. The benchmark pins CSLib v4.29.0 at commit 0d37cc7fcc985cfc53b155e7eef2453f846c6da2, builds with Lean 4.29.0, and evaluates a strict import/source-order task set with 801 proxy-labelable tasks and 1875 CSLib candidate declarations. The labels are"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CSG-Rerank gives a modest early-rank MRR gain over lexical BM25 under the strict policy, but does not reliably outperform BM25+symbol and does not improve Recall@10.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The source-visible proxy labels from proof references accurately stand in for the premises that would actually be needed in a realistic proof-generation or proof-repair setting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CSLibPremiseBench shows that a structure-guided reranker provides only modest MRR gains over BM25 for premise retrieval in Lean 4 CS theorems and does not improve Recall@10.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5af6aa15496abeae1536dd27d6e1b7a699fbbb412810a8fbd768c42e3c39994c"},"source":{"id":"2605.14549","kind":"arxiv","version":1},"verdict":{"id":"a064f180-b8bc-4063-b740-90574b937d56","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:27:08.827243Z","strongest_claim":"CSG-Rerank gives a modest early-rank MRR gain over lexical BM25 under the strict policy, but does not reliably outperform BM25+symbol and does not improve Recall@10.","one_line_summary":"CSLibPremiseBench shows that a structure-guided reranker provides only modest MRR gains over BM25 for premise retrieval in Lean 4 CS theorems and does not improve Recall@10.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The source-visible proxy labels from proof references accurately stand in for the premises that would actually be needed in a realistic proof-generation or proof-repair setting.","pith_extraction_headline":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval."},"references":{"count":16,"sample":[{"doi":"","year":2025,"title":"Leanexplore: A search engine for lean 4 declarations, 2025","work_id":"caf84e7b-650a-41e6-9de3-fe9a418e9ba8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Ayers, Dragomir Radev, and Jeremy Avigad","work_id":"fa9350a1-82e0-40b6-84c8-9b63af97ad6b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Cslib: The lean computer science library, 2026","work_id":"183e90e1-b20e-409a-9cab-8a2fe5aebed8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"The lean 4 theorem prover and programming language, 2021","work_id":"44987b9c-b745-4852-aee6-d3d9e9f8ccf0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Computer science as infrastructure: the spine of the lean computer science library (cslib), 2026","work_id":"e7f1f2b8-0e8d-4475-8ada-1ab1b1d021a1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"cce310dbdecb00c476262cbad61cd6fd9f61c4398322b1bf2ed559efb5058bcd","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":"2605.14549","created_at":"2026-05-17T23:39:05.729797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14549v1","created_at":"2026-05-17T23:39:05.729797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14549","created_at":"2026-05-17T23:39:05.729797+00:00"},{"alias_kind":"pith_short_12","alias_value":"65LENYMP5AEO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"65LENYMP5AEO5CT7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"65LENYMP","created_at":"2026-05-18T12:33:37.589309+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/65LENYMP5AEO5CT7VDCCD3AU2O","json":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O.json","graph_json":"https://pith.science/api/pith-number/65LENYMP5AEO5CT7VDCCD3AU2O/graph.json","events_json":"https://pith.science/api/pith-number/65LENYMP5AEO5CT7VDCCD3AU2O/events.json","paper":"https://pith.science/paper/65LENYMP"},"agent_actions":{"view_html":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O","download_json":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O.json","view_paper":"https://pith.science/paper/65LENYMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14549&json=true","fetch_graph":"https://pith.science/api/pith-number/65LENYMP5AEO5CT7VDCCD3AU2O/graph.json","fetch_events":"https://pith.science/api/pith-number/65LENYMP5AEO5CT7VDCCD3AU2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O/action/storage_attestation","attest_author":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O/action/author_attestation","sign_citation":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O/action/citation_signature","submit_replication":"https://pith.science/pith/65LENYMP5AEO5CT7VDCCD3AU2O/action/replication_record"}},"created_at":"2026-05-17T23:39:05.729797+00:00","updated_at":"2026-05-17T23:39:05.729797+00:00"}