{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VTNFNUPBRKEGB3YUVPLFU4BT2P","short_pith_number":"pith:VTNFNUPB","schema_version":"1.0","canonical_sha256":"acda56d1e18a8860ef14abd65a7033d3cd12ae7a63451ae6c12ab0afae4be2d0","source":{"kind":"arxiv","id":"1908.03830","version":1},"attestation_state":"computed","paper":{"title":"Supervised Negative Binomial Classifier for Probabilistic Record Linkage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harish Kashyap K, Kiran Byadarhaly, Saumya Shah","submitted_at":"2019-08-11T00:25:13Z","abstract_excerpt":"Motivated by the need of the linking records across various databases, we propose a novel graphical model based classifier that uses a mixture of Poisson distributions with latent variables. The idea is to derive insight into each pair of hypothesis records that match by inferring its underlying latent rate of error using Bayesian Modeling techniques. The novel approach of using gamma priors for learning the latent variables along with supervised labels is unique and allows for active learning. The naive assumption is made deliberately as to the independence of the fields to propose a generali"},"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":"1908.03830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-11T00:25:13Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"d9508408622e543a50245cb8b66e4b9213a275ff1d1c12f5f726e966dd4dc378","abstract_canon_sha256":"e9a278b33279c9848e9cbedab3ddfc6204fae562b957e880194abbe372fccdb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:18.572700Z","signature_b64":"PJWOh9Fmc/h1FESlAxTzfxYZCphTGxT1/hDvP4GThhEG+klRSdJ+iTQ6Zhd2urf8c8m44l8+8DQdc8T8UY91DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acda56d1e18a8860ef14abd65a7033d3cd12ae7a63451ae6c12ab0afae4be2d0","last_reissued_at":"2026-07-04T23:53:18.572263Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:18.572263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Negative Binomial Classifier for Probabilistic Record Linkage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harish Kashyap K, Kiran Byadarhaly, Saumya Shah","submitted_at":"2019-08-11T00:25:13Z","abstract_excerpt":"Motivated by the need of the linking records across various databases, we propose a novel graphical model based classifier that uses a mixture of Poisson distributions with latent variables. The idea is to derive insight into each pair of hypothesis records that match by inferring its underlying latent rate of error using Bayesian Modeling techniques. The novel approach of using gamma priors for learning the latent variables along with supervised labels is unique and allows for active learning. The naive assumption is made deliberately as to the independence of the fields to propose a generali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03830","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/1908.03830/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":"1908.03830","created_at":"2026-07-04T23:53:18.572347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03830v1","created_at":"2026-07-04T23:53:18.572347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03830","created_at":"2026-07-04T23:53:18.572347+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTNFNUPBRKEG","created_at":"2026-07-04T23:53:18.572347+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTNFNUPBRKEGB3YU","created_at":"2026-07-04T23:53:18.572347+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTNFNUPB","created_at":"2026-07-04T23:53:18.572347+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/VTNFNUPBRKEGB3YUVPLFU4BT2P","json":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P.json","graph_json":"https://pith.science/api/pith-number/VTNFNUPBRKEGB3YUVPLFU4BT2P/graph.json","events_json":"https://pith.science/api/pith-number/VTNFNUPBRKEGB3YUVPLFU4BT2P/events.json","paper":"https://pith.science/paper/VTNFNUPB"},"agent_actions":{"view_html":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P","download_json":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P.json","view_paper":"https://pith.science/paper/VTNFNUPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03830&json=true","fetch_graph":"https://pith.science/api/pith-number/VTNFNUPBRKEGB3YUVPLFU4BT2P/graph.json","fetch_events":"https://pith.science/api/pith-number/VTNFNUPBRKEGB3YUVPLFU4BT2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P/action/storage_attestation","attest_author":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P/action/author_attestation","sign_citation":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P/action/citation_signature","submit_replication":"https://pith.science/pith/VTNFNUPBRKEGB3YUVPLFU4BT2P/action/replication_record"}},"created_at":"2026-07-04T23:53:18.572347+00:00","updated_at":"2026-07-04T23:53:18.572347+00:00"}