{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DHMPSN62WVPRKLCQCUT57ZLVQ2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"acaf23b0a13079d453458952abd060e38e34c6a0eec258df74a7e19e09f57cb3","cross_cats_sorted":["cs.IR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T12:34:33Z","title_canon_sha256":"65554c5e6f603ccbaa9caefb089aa5e3a014977361a6dd274395d3abb251108e"},"schema_version":"1.0","source":{"id":"2403.16702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16702","created_at":"2026-07-05T08:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16702v1","created_at":"2026-07-05T08:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16702","created_at":"2026-07-05T08:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"DHMPSN62WVPR","created_at":"2026-07-05T08:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"DHMPSN62WVPRKLCQ","created_at":"2026-07-05T08:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"DHMPSN62","created_at":"2026-07-05T08:00:20Z"}],"graph_snapshots":[{"event_id":"sha256:87af13e9cf2f1b6f2301ccf94b80040f33af57fd3987ca950aa75045d3498eba","target":"graph","created_at":"2026-07-05T08:00:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.16702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code representations. In this paper, we introduce ProCQA, a large-scale programming question answering dataset extracted from the StackOverflow community, offering naturally structured mixed-modal QA pairs. To validate its effectiveness, we propose a modality-agnostic contrastive pre-training approach to improve the alignment of text and code representations of ","authors_text":"Chuantao Yin, Jianfei Zhang, Wenge Rong, Yuanxin Ouyang, Zehan Li","cross_cats":["cs.IR","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T12:34:33Z","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16702","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:782b66bb501bf8627fa499d8be99d60314c48007e01abf627fc897b1aa5e566b","target":"record","created_at":"2026-07-05T08:00:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"acaf23b0a13079d453458952abd060e38e34c6a0eec258df74a7e19e09f57cb3","cross_cats_sorted":["cs.IR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T12:34:33Z","title_canon_sha256":"65554c5e6f603ccbaa9caefb089aa5e3a014977361a6dd274395d3abb251108e"},"schema_version":"1.0","source":{"id":"2403.16702","kind":"arxiv","version":1}},"canonical_sha256":"19d8f937dab55f152c501527dfe57586941643e1c457fea3d3080469d0dfb3bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19d8f937dab55f152c501527dfe57586941643e1c457fea3d3080469d0dfb3bb","first_computed_at":"2026-07-05T08:00:20.095390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:20.095390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aS4Ym8ffKxwVAfmbwnRdL0z79VQ7YlRfQ+KpuhyJMF1lXmZ42UtBiFmWifJb7e8uKTwJveKA5136F+MnzsWaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:20.095862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:782b66bb501bf8627fa499d8be99d60314c48007e01abf627fc897b1aa5e566b","sha256:87af13e9cf2f1b6f2301ccf94b80040f33af57fd3987ca950aa75045d3498eba"],"state_sha256":"0fd828c18a1fdee6a51cee6e64ee164088a5047485472074f12f3da10a1d69c2"}