{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OIN3JWIAEUMO5UI7H5QYYHX7DK","short_pith_number":"pith:OIN3JWIA","canonical_record":{"source":{"id":"2607.19847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:32:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"f6baea71f0e5583d9bab155dd9153554f19d1b6ed5cbd847b25f32f97ceca974","abstract_canon_sha256":"6f8c8f6b3b7371dca46fb8e94dcd6e1bb4122cd8160a9c0b4d2ea10e3562db42"},"schema_version":"1.0"},"canonical_sha256":"721bb4d9002518eed11f3f618c1eff1aae88adcf04824b00de2834be34754ef8","source":{"kind":"arxiv","id":"2607.19847","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19847","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19847v1","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19847","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"OIN3JWIAEUMO","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"OIN3JWIAEUMO5UI7","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"OIN3JWIA","created_at":"2026-07-23T01:24:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OIN3JWIAEUMO5UI7H5QYYHX7DK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:32:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"f6baea71f0e5583d9bab155dd9153554f19d1b6ed5cbd847b25f32f97ceca974","abstract_canon_sha256":"6f8c8f6b3b7371dca46fb8e94dcd6e1bb4122cd8160a9c0b4d2ea10e3562db42"},"schema_version":"1.0"},"canonical_sha256":"721bb4d9002518eed11f3f618c1eff1aae88adcf04824b00de2834be34754ef8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:03.453755Z","signature_b64":"Ed0cTYIvc2k/z+Vh0j7JZBDT9mpd8bq+8o0pvVnIiZ5prbXSum60nzhdyfhPJ78kypuz9ZQRbA/Lkfkgv0XZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"721bb4d9002518eed11f3f618c1eff1aae88adcf04824b00de2834be34754ef8","last_reissued_at":"2026-07-23T01:24:03.452898Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:03.452898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19847","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-23T01:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBM29voQ4axYuEsPDXT5I/eVsS+BtkoRgjeG4mEmE5hOhu7xMBBZeHI9iZkjVjMxez3Jb4YKcxbRF0OKqtHABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:53:50.888795Z"},"content_sha256":"30949a410a4d3c43723791b99d6e63f69fe5c575b409117bacf11a900edd5a39","schema_version":"1.0","event_id":"sha256:30949a410a4d3c43723791b99d6e63f69fe5c575b409117bacf11a900edd5a39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OIN3JWIAEUMO5UI7H5QYYHX7DK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Dongmei Zhang, Haoyu Dong, Junjie Xing, Shi Han, Surajit Chaudhuri, Yeye He, Yurong Liu","submitted_at":"2026-07-22T07:32:09Z","abstract_excerpt":"Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically across rows and columns, they are costly to deploy at scale and tend to be overconfident, often generating hallucinated or false-positive predictions.\n  In this paper, we observe that achieving high-precision missing-value prediction in tables requires a distinct combination of three capabilities: (1) world knowledge, (2) text-based reasoning, and (3) code-based reasoning. We system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19847","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/2607.19847/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-23T01:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isTiVTcDjYbzr/6gODmr/x63H2oJwkUu+3cwmAjC2jziWk0INxVmPJaMb3JHzks/z+cr+S5sjA5z/sdBbf0JDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:53:50.889737Z"},"content_sha256":"20b5ea5c1d1fa3c274708c46138ed9edee11d2f7a18cd7cdf8e6b4865ae8e612","schema_version":"1.0","event_id":"sha256:20b5ea5c1d1fa3c274708c46138ed9edee11d2f7a18cd7cdf8e6b4865ae8e612"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:OIN3JWIAEUMO5UI7H5QYYHX7DK","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.14778/3748191.3748200 resolves to 'Data Imputation with Limited Data Redundancy Using Data Lakes'. A reader following the printed text alone cannot reach it.","snippet":"Data Imputation with Limited Data Redundancy Using Data Lakes.Proc. VLDB Endow.18, 10 (June 2025), 3354–3367. https://doi.org/10.14778/3748191. 3748200","arxiv_id":"2607.19847","detector":"doi_compliance","evidence":{"ref_index":62,"verdict_class":"incontrovertible","resolved_title":"Data Imputation with Limited Data Redundancy Using Data Lakes","printed_excerpt":"10.14778/3748191","reconstructed_doi":"10.14778/3748191.3748200"},"severity":"advisory","ref_index":62,"audited_at":"2026-08-01T11:49:18.193840Z","event_type":"pith.integrity.v1","detected_doi":"10.14778/3748191.3748200","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"849dd2f69ba5f90cf36a801e8ecf0f047a7ddf89ec38342db27d406fe20c2cf4","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"Data Imputation with Limited Data Redundancy Using Data Lakes","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15747,"payload_sha256":"a6225be0503c2ad4be7cc827ccef2629304d4a2c508ac4364b7eebbfec2e79ae","signature_b64":"h+x/h/5QVl0jiM0eBQQQaoWx+e5Mg3mdDVsWpo+52ccINRtCNIoCC0UvXuQsTsL+CPIQhY9IFcZU6cy32fNpAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T11:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qG6p6dHlvxwsQD7iOnmlO+8wUEeVY+MQPtnUgKlSWnSeur15pTvBMCovxLVOl9Oei1dsY8BuO5jWODENF9eBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:53:50.893275Z"},"content_sha256":"309a05d1016b3fb71316487dea76e1ef59c62fbece71e54002780f3f3b25a147","schema_version":"1.0","event_id":"sha256:309a05d1016b3fb71316487dea76e1ef59c62fbece71e54002780f3f3b25a147"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/bundle.json","state_url":"https://pith.science/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T18:53:50Z","links":{"resolver":"https://pith.science/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK","bundle":"https://pith.science/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/bundle.json","state":"https://pith.science/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OIN3JWIAEUMO5UI7H5QYYHX7DK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OIN3JWIAEUMO5UI7H5QYYHX7DK","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6f8c8f6b3b7371dca46fb8e94dcd6e1bb4122cd8160a9c0b4d2ea10e3562db42","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:32:09Z","title_canon_sha256":"f6baea71f0e5583d9bab155dd9153554f19d1b6ed5cbd847b25f32f97ceca974"},"schema_version":"1.0","source":{"id":"2607.19847","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19847","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19847v1","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19847","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"OIN3JWIAEUMO","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"OIN3JWIAEUMO5UI7","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"OIN3JWIA","created_at":"2026-07-23T01:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:20b5ea5c1d1fa3c274708c46138ed9edee11d2f7a18cd7cdf8e6b4865ae8e612","target":"graph","created_at":"2026-07-23T01:24:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.19847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically across rows and columns, they are costly to deploy at scale and tend to be overconfident, often generating hallucinated or false-positive predictions.\n  In this paper, we observe that achieving high-precision missing-value prediction in tables requires a distinct combination of three capabilities: (1) world knowledge, (2) text-based reasoning, and (3) code-based reasoning. We system","authors_text":"Dongmei Zhang, Haoyu Dong, Junjie Xing, Shi Han, Surajit Chaudhuri, Yeye He, Yurong Liu","cross_cats":["cs.AI","cs.CL","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:32:09Z","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19847","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30949a410a4d3c43723791b99d6e63f69fe5c575b409117bacf11a900edd5a39","target":"record","created_at":"2026-07-23T01:24:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6f8c8f6b3b7371dca46fb8e94dcd6e1bb4122cd8160a9c0b4d2ea10e3562db42","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:32:09Z","title_canon_sha256":"f6baea71f0e5583d9bab155dd9153554f19d1b6ed5cbd847b25f32f97ceca974"},"schema_version":"1.0","source":{"id":"2607.19847","kind":"arxiv","version":1}},"canonical_sha256":"721bb4d9002518eed11f3f618c1eff1aae88adcf04824b00de2834be34754ef8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"721bb4d9002518eed11f3f618c1eff1aae88adcf04824b00de2834be34754ef8","first_computed_at":"2026-07-23T01:24:03.452898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:03.452898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ed0cTYIvc2k/z+Vh0j7JZBDT9mpd8bq+8o0pvVnIiZ5prbXSum60nzhdyfhPJ78kypuz9ZQRbA/Lkfkgv0XZAQ==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:03.453755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19847","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30949a410a4d3c43723791b99d6e63f69fe5c575b409117bacf11a900edd5a39","sha256:20b5ea5c1d1fa3c274708c46138ed9edee11d2f7a18cd7cdf8e6b4865ae8e612","sha256:309a05d1016b3fb71316487dea76e1ef59c62fbece71e54002780f3f3b25a147"],"state_sha256":"a0df3d31d608ac9341015a28328159cfec4b5b8602873b2744a59b062b9fa790"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gaObGWY6UyQXjmP2aktFeJNB3PYAFXkPszwfB6ZHIyHKlT9Mt/MjJCGt91j9zA8rRXOxLDjTsWuZRT3hx7LCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:53:50.897722Z","bundle_sha256":"ca2520679752f12d0559480f7a02b818e174da0e393ac4ebe2b2c7f5c208df33"}}