{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JPI44BUOXW42V4YO6DIWUL3T5D","short_pith_number":"pith:JPI44BUO","schema_version":"1.0","canonical_sha256":"4bd1ce068ebdb9aaf30ef0d16a2f73e8c8c895b8170145989de59b22163a386d","source":{"kind":"arxiv","id":"2211.16490","version":1},"attestation_state":"computed","paper":{"title":"Coder Reviewer Reranking for Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Fried, Mike Lewis, Sida I. Wang, Tao Yu, Tatsunori B. Hashimoto, Tianyi Zhang, Wen-tau Yih","submitted_at":"2022-11-29T18:56:33Z","abstract_excerpt":"Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions. Inspired by collaborative programming, we propose Coder-Reviewer reranking. We augment Coder language models from past work, which generate programs given language instructions, with Reviewer models, which evaluate the likelihood of the instruction given the generated programs. We perform an extensive study across six datasets with eight models from three model families. Experimental results show that Coder-Reviewer"},"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":"2211.16490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T18:56:33Z","cross_cats_sorted":["cs.CL","cs.PL","cs.SE"],"title_canon_sha256":"b895a2b0208a40798cb1a88679c880f2d001c443c8f8b59cddf0ff2b5389d4d6","abstract_canon_sha256":"6060d619b32089ce2b1fdf5070aef4e1178c4f3e22c32ea12c5973b67e4b11a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:27.404303Z","signature_b64":"znFHbum7Hiq1ucMFmJU928MsV2wNGryV9q1J8eNxjjx5hQNnMvxqVWjCwwQjmzjkDdBW+VMSV1KzFfezIhJsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd1ce068ebdb9aaf30ef0d16a2f73e8c8c895b8170145989de59b22163a386d","last_reissued_at":"2026-07-05T05:20:27.403906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:27.403906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coder Reviewer Reranking for Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Fried, Mike Lewis, Sida I. Wang, Tao Yu, Tatsunori B. Hashimoto, Tianyi Zhang, Wen-tau Yih","submitted_at":"2022-11-29T18:56:33Z","abstract_excerpt":"Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions. Inspired by collaborative programming, we propose Coder-Reviewer reranking. We augment Coder language models from past work, which generate programs given language instructions, with Reviewer models, which evaluate the likelihood of the instruction given the generated programs. We perform an extensive study across six datasets with eight models from three model families. Experimental results show that Coder-Reviewer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16490","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/2211.16490/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":"2211.16490","created_at":"2026-07-05T05:20:27.403962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16490v1","created_at":"2026-07-05T05:20:27.403962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16490","created_at":"2026-07-05T05:20:27.403962+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPI44BUOXW42","created_at":"2026-07-05T05:20:27.403962+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPI44BUOXW42V4YO","created_at":"2026-07-05T05:20:27.403962+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPI44BUO","created_at":"2026-07-05T05:20:27.403962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.05128","citing_title":"Teaching Large Language Models to Self-Debug","ref_index":140,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D","json":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D.json","graph_json":"https://pith.science/api/pith-number/JPI44BUOXW42V4YO6DIWUL3T5D/graph.json","events_json":"https://pith.science/api/pith-number/JPI44BUOXW42V4YO6DIWUL3T5D/events.json","paper":"https://pith.science/paper/JPI44BUO"},"agent_actions":{"view_html":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D","download_json":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D.json","view_paper":"https://pith.science/paper/JPI44BUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16490&json=true","fetch_graph":"https://pith.science/api/pith-number/JPI44BUOXW42V4YO6DIWUL3T5D/graph.json","fetch_events":"https://pith.science/api/pith-number/JPI44BUOXW42V4YO6DIWUL3T5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D/action/storage_attestation","attest_author":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D/action/author_attestation","sign_citation":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D/action/citation_signature","submit_replication":"https://pith.science/pith/JPI44BUOXW42V4YO6DIWUL3T5D/action/replication_record"}},"created_at":"2026-07-05T05:20:27.403962+00:00","updated_at":"2026-07-05T05:20:27.403962+00:00"}