{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JTIOCR53ODP7MP2EOIFXISGRUJ","short_pith_number":"pith:JTIOCR53","schema_version":"1.0","canonical_sha256":"4cd0e147bb70dff63f44720b7448d1a254e3dc00e62c0663d130926f3ee242f3","source":{"kind":"arxiv","id":"2305.17145","version":1},"attestation_state":"computed","paper":{"title":"Type Prediction With Program Decomposition and Fill-in-the-Type Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Arjun Guha, Federico Cassano, Ming-Ho Yee, Noah Shinn, Steven Holtzen","submitted_at":"2023-05-25T21:16:09Z","abstract_excerpt":"TypeScript and Python are two programming languages that support optional type annotations, which are useful but tedious to introduce and maintain. This has motivated automated type prediction: given an untyped program, produce a well-typed output program. Large language models (LLMs) are promising for type prediction, but there are challenges: fill-in-the-middle performs poorly, programs may not fit into the context window, generated types may not type check, and it is difficult to measure how well-typed the output program is. We address these challenges by building OpenTau, a search-based ap"},"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":"2305.17145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-25T21:16:09Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"6f6e839b5b7649f4fcfac553735d3ee400693b7fadfdf0dc205500fcd5c6809b","abstract_canon_sha256":"3241e6612d59e8aa07fa656c0693704895925effee70e3cfac97e235df029e8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:44.029616Z","signature_b64":"H1ofMGtWC98DNTRPCYWm/WKQXCPSfYqVRJsdZV+91s51/qBM5VrIJ4xgRwOHZw5FZGCSyI5+p0H4Gd6IBLWiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd0e147bb70dff63f44720b7448d1a254e3dc00e62c0663d130926f3ee242f3","last_reissued_at":"2026-07-05T06:14:44.029274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:44.029274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Type Prediction With Program Decomposition and Fill-in-the-Type Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Arjun Guha, Federico Cassano, Ming-Ho Yee, Noah Shinn, Steven Holtzen","submitted_at":"2023-05-25T21:16:09Z","abstract_excerpt":"TypeScript and Python are two programming languages that support optional type annotations, which are useful but tedious to introduce and maintain. This has motivated automated type prediction: given an untyped program, produce a well-typed output program. Large language models (LLMs) are promising for type prediction, but there are challenges: fill-in-the-middle performs poorly, programs may not fit into the context window, generated types may not type check, and it is difficult to measure how well-typed the output program is. We address these challenges by building OpenTau, a search-based ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17145","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/2305.17145/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":"2305.17145","created_at":"2026-07-05T06:14:44.029335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17145v1","created_at":"2026-07-05T06:14:44.029335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17145","created_at":"2026-07-05T06:14:44.029335+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTIOCR53ODP7","created_at":"2026-07-05T06:14:44.029335+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTIOCR53ODP7MP2E","created_at":"2026-07-05T06:14:44.029335+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTIOCR53","created_at":"2026-07-05T06:14:44.029335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15368","citing_title":"The Power of Types: Exploring the Impact of Type Checking on Neural Bug Detection in Dynamically Typed Languages","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ","json":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ.json","graph_json":"https://pith.science/api/pith-number/JTIOCR53ODP7MP2EOIFXISGRUJ/graph.json","events_json":"https://pith.science/api/pith-number/JTIOCR53ODP7MP2EOIFXISGRUJ/events.json","paper":"https://pith.science/paper/JTIOCR53"},"agent_actions":{"view_html":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ","download_json":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ.json","view_paper":"https://pith.science/paper/JTIOCR53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17145&json=true","fetch_graph":"https://pith.science/api/pith-number/JTIOCR53ODP7MP2EOIFXISGRUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JTIOCR53ODP7MP2EOIFXISGRUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ/action/storage_attestation","attest_author":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ/action/author_attestation","sign_citation":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ/action/citation_signature","submit_replication":"https://pith.science/pith/JTIOCR53ODP7MP2EOIFXISGRUJ/action/replication_record"}},"created_at":"2026-07-05T06:14:44.029335+00:00","updated_at":"2026-07-05T06:14:44.029335+00:00"}