{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J4Q27ZQWGK52AWPIYDBJPIGDDT","short_pith_number":"pith:J4Q27ZQW","schema_version":"1.0","canonical_sha256":"4f21afe61632bba059e8c0c297a0c31ccaa7a78a10b796a22d1c560c6f589bdf","source":{"kind":"arxiv","id":"2107.11423","version":1},"attestation_state":"computed","paper":{"title":"Ensemble Models for Neural Source Code Summarization of Subroutines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aakash Bansal, Alexander LeClair, Collin McMillan","submitted_at":"2021-07-23T19:12:55Z","abstract_excerpt":"A source code summary of a subroutine is a brief description of that subroutine. Summaries underpin a majority of documentation consumed by programmers, such as the method summaries in JavaDocs. Source code summarization is the task of writing these summaries. At present, most state-of-the-art approaches for code summarization are neural network-based solutions akin to seq2seq, graph2seq, and other encoder-decoder architectures. The input to the encoder is source code, while the decoder helps predict the natural language summary. While these models tend to be similar in structure, evidence is "},"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":"2107.11423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-07-23T19:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"d344a31c07757fe4f43af84caaa44dec81d21b15ccc2720ffabc469521f45f3a","abstract_canon_sha256":"3277b458a67156b6271e7d7e6073b431f5da8082a481e8bb0a9a01de6d526c6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:19.258036Z","signature_b64":"4jkIhEijI+Uv9gWRWITmo1okydGawZgJrNtn5SRnX+lPrlMsxogq+dRZEVdmc2Jsz/JvJqdond/MM6sWdJXyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f21afe61632bba059e8c0c297a0c31ccaa7a78a10b796a22d1c560c6f589bdf","last_reissued_at":"2026-07-05T03:00:19.257644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:19.257644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Models for Neural Source Code Summarization of Subroutines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aakash Bansal, Alexander LeClair, Collin McMillan","submitted_at":"2021-07-23T19:12:55Z","abstract_excerpt":"A source code summary of a subroutine is a brief description of that subroutine. Summaries underpin a majority of documentation consumed by programmers, such as the method summaries in JavaDocs. Source code summarization is the task of writing these summaries. At present, most state-of-the-art approaches for code summarization are neural network-based solutions akin to seq2seq, graph2seq, and other encoder-decoder architectures. The input to the encoder is source code, while the decoder helps predict the natural language summary. While these models tend to be similar in structure, evidence is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11423","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/2107.11423/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":"2107.11423","created_at":"2026-07-05T03:00:19.257702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11423v1","created_at":"2026-07-05T03:00:19.257702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11423","created_at":"2026-07-05T03:00:19.257702+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4Q27ZQWGK52","created_at":"2026-07-05T03:00:19.257702+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4Q27ZQWGK52AWPI","created_at":"2026-07-05T03:00:19.257702+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4Q27ZQW","created_at":"2026-07-05T03:00:19.257702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22247","citing_title":"Natural Language-Focused Software Engineering via Code-Documentation Equivalence","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT","json":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT.json","graph_json":"https://pith.science/api/pith-number/J4Q27ZQWGK52AWPIYDBJPIGDDT/graph.json","events_json":"https://pith.science/api/pith-number/J4Q27ZQWGK52AWPIYDBJPIGDDT/events.json","paper":"https://pith.science/paper/J4Q27ZQW"},"agent_actions":{"view_html":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT","download_json":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT.json","view_paper":"https://pith.science/paper/J4Q27ZQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11423&json=true","fetch_graph":"https://pith.science/api/pith-number/J4Q27ZQWGK52AWPIYDBJPIGDDT/graph.json","fetch_events":"https://pith.science/api/pith-number/J4Q27ZQWGK52AWPIYDBJPIGDDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT/action/storage_attestation","attest_author":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT/action/author_attestation","sign_citation":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT/action/citation_signature","submit_replication":"https://pith.science/pith/J4Q27ZQWGK52AWPIYDBJPIGDDT/action/replication_record"}},"created_at":"2026-07-05T03:00:19.257702+00:00","updated_at":"2026-07-05T03:00:19.257702+00:00"}