{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L2WOOGJDDCNXDDOXXKGCSJIUO5","short_pith_number":"pith:L2WOOGJD","canonical_record":{"source":{"id":"2406.15483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:42:13Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"b28ea08b48c7ca9ed6071dad3a4047f61e023f385462163caba7c96b79a17d8a","abstract_canon_sha256":"77c014cb9765822b9b9187d5060ea2efed01746facbb4970096d12c8c7316c87"},"schema_version":"1.0"},"canonical_sha256":"5eace71923189b718dd7ba8c2925147740fd2faf9207122de411dc225979aed8","source":{"kind":"arxiv","id":"2406.15483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15483","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15483v1","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15483","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_12","alias_value":"L2WOOGJDDCNX","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_16","alias_value":"L2WOOGJDDCNXDDOX","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_8","alias_value":"L2WOOGJD","created_at":"2026-07-05T08:35:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L2WOOGJDDCNXDDOXXKGCSJIUO5","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:42:13Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"b28ea08b48c7ca9ed6071dad3a4047f61e023f385462163caba7c96b79a17d8a","abstract_canon_sha256":"77c014cb9765822b9b9187d5060ea2efed01746facbb4970096d12c8c7316c87"},"schema_version":"1.0"},"canonical_sha256":"5eace71923189b718dd7ba8c2925147740fd2faf9207122de411dc225979aed8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:23.136942Z","signature_b64":"FncPt1pL8wcuVL5tO/z4yv5JbXs6Vyz/56Ehu4lrh3XmN5YblDU5hjQXKidbhqhL9DdM2PXHbUxdfENm4UVRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eace71923189b718dd7ba8c2925147740fd2faf9207122de411dc225979aed8","last_reissued_at":"2026-07-05T08:35:23.136438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:23.136438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15483","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":"2026-07-05T08:35:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wx0MxvOwDFnRigud6Eg16rSQC+eTjUv7inh/h51usRsgrL9FYa7yKOwsfM+W69+FvNFlaA25GfIvzKCHuZpoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:54:05.004675Z"},"content_sha256":"86609e612a89759a712eb7f58ea13316c3a2cf50ffaae902f1c66baed2441019","schema_version":"1.0","event_id":"sha256:86609e612a89759a712eb7f58ea13316c3a2cf50ffaae902f1c66baed2441019"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L2WOOGJDDCNXDDOXXKGCSJIUO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Duplicate Detection with GenAI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ian Ormesher","submitted_at":"2024-06-17T06:42:13Z","abstract_excerpt":"Customer data is often stored as records in Customer Relations Management systems (CRMs). Data which is manually entered into such systems by one of more users over time leads to data replication, partial duplication or fuzzy duplication. This in turn means that there no longer a single source of truth for customers, contacts, accounts, etc. Downstream business processes become increasing complex and contrived without a unique mapping between a record in a CRM and the target customer. Current methods to detect and de-duplicate records use traditional Natural Language Processing techniques know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15483","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/2406.15483/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":"2026-07-05T08:35:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNYuVOIAoQO8CsySSeTDWWhgDs4gC5yUfSk1fUgfIZ/OeR4FCBaYp0QLZ8OB21/QGQwAbcCxSw/jo7UC5facAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:54:05.005209Z"},"content_sha256":"cf357a8847c6b04b1c101c9f865f1bff741d1681f9ae0a9eb8562342216de38d","schema_version":"1.0","event_id":"sha256:cf357a8847c6b04b1c101c9f865f1bff741d1681f9ae0a9eb8562342216de38d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/bundle.json","state_url":"https://pith.science/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/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":"2026-08-18T17:54:05Z","links":{"resolver":"https://pith.science/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5","bundle":"https://pith.science/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/bundle.json","state":"https://pith.science/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2WOOGJDDCNXDDOXXKGCSJIUO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L2WOOGJDDCNXDDOXXKGCSJIUO5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"77c014cb9765822b9b9187d5060ea2efed01746facbb4970096d12c8c7316c87","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:42:13Z","title_canon_sha256":"b28ea08b48c7ca9ed6071dad3a4047f61e023f385462163caba7c96b79a17d8a"},"schema_version":"1.0","source":{"id":"2406.15483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15483","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15483v1","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15483","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_12","alias_value":"L2WOOGJDDCNX","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_16","alias_value":"L2WOOGJDDCNXDDOX","created_at":"2026-07-05T08:35:23Z"},{"alias_kind":"pith_short_8","alias_value":"L2WOOGJD","created_at":"2026-07-05T08:35:23Z"}],"graph_snapshots":[{"event_id":"sha256:cf357a8847c6b04b1c101c9f865f1bff741d1681f9ae0a9eb8562342216de38d","target":"graph","created_at":"2026-07-05T08:35:23Z","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/2406.15483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Customer data is often stored as records in Customer Relations Management systems (CRMs). Data which is manually entered into such systems by one of more users over time leads to data replication, partial duplication or fuzzy duplication. This in turn means that there no longer a single source of truth for customers, contacts, accounts, etc. Downstream business processes become increasing complex and contrived without a unique mapping between a record in a CRM and the target customer. Current methods to detect and de-duplicate records use traditional Natural Language Processing techniques know","authors_text":"Ian Ormesher","cross_cats":["cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:42:13Z","title":"Duplicate Detection with GenAI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15483","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":"sha256:86609e612a89759a712eb7f58ea13316c3a2cf50ffaae902f1c66baed2441019","target":"record","created_at":"2026-07-05T08:35:23Z","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":"77c014cb9765822b9b9187d5060ea2efed01746facbb4970096d12c8c7316c87","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:42:13Z","title_canon_sha256":"b28ea08b48c7ca9ed6071dad3a4047f61e023f385462163caba7c96b79a17d8a"},"schema_version":"1.0","source":{"id":"2406.15483","kind":"arxiv","version":1}},"canonical_sha256":"5eace71923189b718dd7ba8c2925147740fd2faf9207122de411dc225979aed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eace71923189b718dd7ba8c2925147740fd2faf9207122de411dc225979aed8","first_computed_at":"2026-07-05T08:35:23.136438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:23.136438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FncPt1pL8wcuVL5tO/z4yv5JbXs6Vyz/56Ehu4lrh3XmN5YblDU5hjQXKidbhqhL9DdM2PXHbUxdfENm4UVRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:23.136942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86609e612a89759a712eb7f58ea13316c3a2cf50ffaae902f1c66baed2441019","sha256:cf357a8847c6b04b1c101c9f865f1bff741d1681f9ae0a9eb8562342216de38d"],"state_sha256":"b7201646b057c596b4481fe1c68d922184098cefe524c2fe96900227ed0cd51b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSnZDRFYGlXN1KzCiPPHzrEkLAbnZmVXo8IW4VIjWq1e6OMDHp5+451Z1CoqR9FueN82TZocPxo/Q+goTDYZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:54:05.010813Z","bundle_sha256":"48348509824eeebc612b929a4a339902be9188501bac40ea2330d1a9a03c3589"}}