{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6U2IP2YEWDKE4C2RZBDJ3K3VM7","short_pith_number":"pith:6U2IP2YE","schema_version":"1.0","canonical_sha256":"f53487eb04b0d44e0b51c8469dab7567d7a1ccba08343408aa03989b81c9dd1d","source":{"kind":"arxiv","id":"2606.07519","version":1},"attestation_state":"computed","paper":{"title":"Bidirectional Small-Granularity Search between Code and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Clayton T. Morrison, Enrique Noriega-Atala, Gus Hahn-Powell, Marco A. Valenzuela-Esc\\'arcega, Mihai Surdeanu","submitted_at":"2026-04-19T03:19:59Z","abstract_excerpt":"We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and the results are also small fragments of the opposite modality, i.e., code or text. This task establishes direct links between text in scientific publications and corresponding code segments, in support of better and faster understanding of scientific methods. We introduce a large dataset for the proposed task that includes a training partition with textual descriptions of code generated automatically using GPT-4, and three testing partitions, one"},"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":"2606.07519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T03:19:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9fb28d5c716faecd2de7dce4bf8cd820ff1f0b3563c7cf4322e3f32c95cf408","abstract_canon_sha256":"54d704909e3ac322a414e54d37c14212163d0a3650502fe279962896e40763fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:41.169262Z","signature_b64":"Flms3Kv+41nugo0p9f+RCVjwGGt4MVoR+7gErCUeG8cmsLxcb4ZHwg3/iH8kKN/E6OaRh3BWMx8X8fzC5DYoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53487eb04b0d44e0b51c8469dab7567d7a1ccba08343408aa03989b81c9dd1d","last_reissued_at":"2026-06-09T00:04:41.168552Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:41.168552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Small-Granularity Search between Code and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Clayton T. Morrison, Enrique Noriega-Atala, Gus Hahn-Powell, Marco A. Valenzuela-Esc\\'arcega, Mihai Surdeanu","submitted_at":"2026-04-19T03:19:59Z","abstract_excerpt":"We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and the results are also small fragments of the opposite modality, i.e., code or text. This task establishes direct links between text in scientific publications and corresponding code segments, in support of better and faster understanding of scientific methods. We introduce a large dataset for the proposed task that includes a training partition with textual descriptions of code generated automatically using GPT-4, and three testing partitions, one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07519","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/2606.07519/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":"2606.07519","created_at":"2026-06-09T00:04:41.168648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07519v1","created_at":"2026-06-09T00:04:41.168648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07519","created_at":"2026-06-09T00:04:41.168648+00:00"},{"alias_kind":"pith_short_12","alias_value":"6U2IP2YEWDKE","created_at":"2026-06-09T00:04:41.168648+00:00"},{"alias_kind":"pith_short_16","alias_value":"6U2IP2YEWDKE4C2R","created_at":"2026-06-09T00:04:41.168648+00:00"},{"alias_kind":"pith_short_8","alias_value":"6U2IP2YE","created_at":"2026-06-09T00:04:41.168648+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/6U2IP2YEWDKE4C2RZBDJ3K3VM7","json":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7.json","graph_json":"https://pith.science/api/pith-number/6U2IP2YEWDKE4C2RZBDJ3K3VM7/graph.json","events_json":"https://pith.science/api/pith-number/6U2IP2YEWDKE4C2RZBDJ3K3VM7/events.json","paper":"https://pith.science/paper/6U2IP2YE"},"agent_actions":{"view_html":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7","download_json":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7.json","view_paper":"https://pith.science/paper/6U2IP2YE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07519&json=true","fetch_graph":"https://pith.science/api/pith-number/6U2IP2YEWDKE4C2RZBDJ3K3VM7/graph.json","fetch_events":"https://pith.science/api/pith-number/6U2IP2YEWDKE4C2RZBDJ3K3VM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7/action/storage_attestation","attest_author":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7/action/author_attestation","sign_citation":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7/action/citation_signature","submit_replication":"https://pith.science/pith/6U2IP2YEWDKE4C2RZBDJ3K3VM7/action/replication_record"}},"created_at":"2026-06-09T00:04:41.168648+00:00","updated_at":"2026-06-09T00:04:41.168648+00:00"}