{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GHVQR7JSRFWBHXL35E5OQQNN4F","short_pith_number":"pith:GHVQR7JS","schema_version":"1.0","canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","source":{"kind":"arxiv","id":"1904.02660","version":1},"attestation_state":"computed","paper":{"title":"Recommendations for Datasets for Source Code Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander LeClair, Collin McMillan","submitted_at":"2019-04-04T16:56:01Z","abstract_excerpt":"Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code summarization is rapidly becoming a popular research problem, but progress is restrained due to a lack of suitable datasets. In addition, a lack of community standards for creating datasets leads to confusing and unreproducible research results -- we observe swings in performance of more than 33% due only to changes in dataset design. In this paper, we make recommen"},"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":"1904.02660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"c09552e0e27e4a41c966252d29e372fa15f7503aa99117370725887f28c3bcdf","abstract_canon_sha256":"30e00dcbcfd8b000e7b2bf342574f97528d5152c804d7a87e24a141cd520df47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.085525Z","signature_b64":"ZA1/XiCDoKG2OsTBmH5cDJBuUtW6Aqw2/x9iWfKct9d1uJ01eTMyHugNTYhN0FVgRJkvew5il+TVJRhIiFrMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","last_reissued_at":"2026-05-17T23:49:23.084973Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.084973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommendations for Datasets for Source Code Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander LeClair, Collin McMillan","submitted_at":"2019-04-04T16:56:01Z","abstract_excerpt":"Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code summarization is rapidly becoming a popular research problem, but progress is restrained due to a lack of suitable datasets. In addition, a lack of community standards for creating datasets leads to confusing and unreproducible research results -- we observe swings in performance of more than 33% due only to changes in dataset design. In this paper, we make recommen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02660","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":""},"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":"1904.02660","created_at":"2026-05-17T23:49:23.085047+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02660v1","created_at":"2026-05-17T23:49:23.085047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02660","created_at":"2026-05-17T23:49:23.085047+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHVQR7JSRFWB","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHVQR7JSRFWBHXL3","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHVQR7JS","created_at":"2026-05-18T12:33:18.533446+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/GHVQR7JSRFWBHXL35E5OQQNN4F","json":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F.json","graph_json":"https://pith.science/api/pith-number/GHVQR7JSRFWBHXL35E5OQQNN4F/graph.json","events_json":"https://pith.science/api/pith-number/GHVQR7JSRFWBHXL35E5OQQNN4F/events.json","paper":"https://pith.science/paper/GHVQR7JS"},"agent_actions":{"view_html":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F","download_json":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F.json","view_paper":"https://pith.science/paper/GHVQR7JS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02660&json=true","fetch_graph":"https://pith.science/api/pith-number/GHVQR7JSRFWBHXL35E5OQQNN4F/graph.json","fetch_events":"https://pith.science/api/pith-number/GHVQR7JSRFWBHXL35E5OQQNN4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/action/storage_attestation","attest_author":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/action/author_attestation","sign_citation":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/action/citation_signature","submit_replication":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/action/replication_record"}},"created_at":"2026-05-17T23:49:23.085047+00:00","updated_at":"2026-05-17T23:49:23.085047+00:00"}