{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GNXKM5JU7HC6Y7C7U3XW3IA3QZ","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":"7cdf0a10b31ca1227839f7df3acaad4c06860e8567d98fb373bc49ceeae7321c","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T03:39:04Z","title_canon_sha256":"6db2baa02c95ac9f595619b5dddb7188f8dbf758c6d58fb48770271e07fe7b20"},"schema_version":"1.0","source":{"id":"1805.08949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08949","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08949v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08949","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"GNXKM5JU7HC6","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GNXKM5JU7HC6Y7C7","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GNXKM5JU","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:c95aacc4f944c6f88bae0d34643366c3d343f7b67f1e180baaca1cecaae98b85","target":"graph","created_at":"2026-05-18T00:15:08Z","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"},"paper":{"abstract_excerpt":"For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with fine-grained alignments. Stack Overflow (SO) is a promising source to create such a data set: the questions are diverse and most of them have corresponding answers with high-quality code snippets. However, existing heuristic methods (e.g., pairing the title of a post with the code in the accepted answer) are limited both in their coverage and the correctness of t","authors_text":"Bogdan Vasilescu, Bowen Deng, Edgar Chen, Graham Neubig, Pengcheng Yin","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T03:39:04Z","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08949","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":"sha256:35b973ef347b88df0197b948ffe685c94528200deda666fb22fadc49c4455419","target":"record","created_at":"2026-05-18T00:15:08Z","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":"7cdf0a10b31ca1227839f7df3acaad4c06860e8567d98fb373bc49ceeae7321c","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T03:39:04Z","title_canon_sha256":"6db2baa02c95ac9f595619b5dddb7188f8dbf758c6d58fb48770271e07fe7b20"},"schema_version":"1.0","source":{"id":"1805.08949","kind":"arxiv","version":1}},"canonical_sha256":"336ea67534f9c5ec7c5fa6ef6da01b8651a5b023a61cde34bddb5bf43455271a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"336ea67534f9c5ec7c5fa6ef6da01b8651a5b023a61cde34bddb5bf43455271a","first_computed_at":"2026-05-18T00:15:08.982098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:08.982098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20wIxHPit+DWYRxbGzpoTpWQHcQ7WdeslOX0YF08jK8iQr4hbYFmBXO8DCRkf5M0yIPdISPTzqA+pVxRRopmCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:08.982605Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35b973ef347b88df0197b948ffe685c94528200deda666fb22fadc49c4455419","sha256:c95aacc4f944c6f88bae0d34643366c3d343f7b67f1e180baaca1cecaae98b85"],"state_sha256":"ecacb9b694b63f626e795c0b92802daa700af5aa509ee0ef5ad2b290447d1981"}