{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NA56566RO6XX23FZ6OJGCMFNBT","short_pith_number":"pith:NA56566R","canonical_record":{"source":{"id":"2308.00721","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T03:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4ce088436cb294134b3bf0b84a8909793476872f67719d9d77d4ec9908bb63e","abstract_canon_sha256":"d4e0d99417003625bf2828cb64a807862563a3ca2946359af4953ffe628d3c48"},"schema_version":"1.0"},"canonical_sha256":"683beefbd177af7d6cb9f3926130ad0cce31a15f24f781da3fc8614cad859935","source":{"kind":"arxiv","id":"2308.00721","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.00721","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.00721v4","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00721","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"NA56566RO6XX","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"NA56566RO6XX23FZ","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"NA56566R","created_at":"2026-07-05T09:59:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NA56566RO6XX23FZ6OJGCMFNBT","target":"record","payload":{"canonical_record":{"source":{"id":"2308.00721","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T03:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4ce088436cb294134b3bf0b84a8909793476872f67719d9d77d4ec9908bb63e","abstract_canon_sha256":"d4e0d99417003625bf2828cb64a807862563a3ca2946359af4953ffe628d3c48"},"schema_version":"1.0"},"canonical_sha256":"683beefbd177af7d6cb9f3926130ad0cce31a15f24f781da3fc8614cad859935","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:12.313075Z","signature_b64":"O9DMf60/0QdfRgawNHJv04tT/aAhfVRz06iXZXwK0vyjVxh8RUldSCB1ZZtK3cNLerBno5LWZmjci4qczoQPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683beefbd177af7d6cb9f3926130ad0cce31a15f24f781da3fc8614cad859935","last_reissued_at":"2026-07-05T09:59:12.312496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:12.312496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.00721","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HL9BUYBAMBtE2fiEYaYbxS9i0VkEi1EHdx80rEhWoogmqkFnCnBA3ra/cUJKfB2c0vWzke6xT0OP6wmXal39CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:51.925836Z"},"content_sha256":"1f752a15cd33029e06e84fbf716a0c9dead96aea60ad985c84a1ace383b652ae","schema_version":"1.0","event_id":"sha256:1f752a15cd33029e06e84fbf716a0c9dead96aea60ad985c84a1ace383b652ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NA56566RO6XX23FZ6OJGCMFNBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Pre-trained Data Deduplication Model based on Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fengmao Lv, Haochen Shi, Hongtao Xue, Jie Hu, Shengdong Du, Tianrui Li, Xinyao Liu","submitted_at":"2023-07-31T03:56:46Z","abstract_excerpt":"In the era of big data, the issue of data quality has become increasingly prominent. One of the main challenges is the problem of duplicate data, which can arise from repeated entry or the merging of multiple data sources. These \"dirty data\" problems can significantly limit the effective application of big data. To address the issue of data deduplication, we propose a pre-trained deduplication model based on active learning, which is the first work that utilizes active learning to address the problem of deduplication at the semantic level. The model is built on a pre-trained Transformer and fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00721","kind":"arxiv","version":4},"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/2308.00721/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":"2026-07-05T09:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5ivRPU6nH4IA1z84cKZYqTNBIHTVEEHNywu7lvmWtdylZtk7c7bGRUarcvVt3Qu1P9EdhXp7vEiSg7MYmiwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:51.926336Z"},"content_sha256":"6c6cc6190c021a5da0cf5c94ed298d81a1a12ad79131723f89c4862b51399016","schema_version":"1.0","event_id":"sha256:6c6cc6190c021a5da0cf5c94ed298d81a1a12ad79131723f89c4862b51399016"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NA56566RO6XX23FZ6OJGCMFNBT/bundle.json","state_url":"https://pith.science/pith/NA56566RO6XX23FZ6OJGCMFNBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NA56566RO6XX23FZ6OJGCMFNBT/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":"2026-08-06T21:52:51Z","links":{"resolver":"https://pith.science/pith/NA56566RO6XX23FZ6OJGCMFNBT","bundle":"https://pith.science/pith/NA56566RO6XX23FZ6OJGCMFNBT/bundle.json","state":"https://pith.science/pith/NA56566RO6XX23FZ6OJGCMFNBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NA56566RO6XX23FZ6OJGCMFNBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NA56566RO6XX23FZ6OJGCMFNBT","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":"d4e0d99417003625bf2828cb64a807862563a3ca2946359af4953ffe628d3c48","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T03:56:46Z","title_canon_sha256":"e4ce088436cb294134b3bf0b84a8909793476872f67719d9d77d4ec9908bb63e"},"schema_version":"1.0","source":{"id":"2308.00721","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.00721","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.00721v4","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00721","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"NA56566RO6XX","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"NA56566RO6XX23FZ","created_at":"2026-07-05T09:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"NA56566R","created_at":"2026-07-05T09:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:6c6cc6190c021a5da0cf5c94ed298d81a1a12ad79131723f89c4862b51399016","target":"graph","created_at":"2026-07-05T09:59:12Z","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/2308.00721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of big data, the issue of data quality has become increasingly prominent. One of the main challenges is the problem of duplicate data, which can arise from repeated entry or the merging of multiple data sources. These \"dirty data\" problems can significantly limit the effective application of big data. To address the issue of data deduplication, we propose a pre-trained deduplication model based on active learning, which is the first work that utilizes active learning to address the problem of deduplication at the semantic level. The model is built on a pre-trained Transformer and fi","authors_text":"Fengmao Lv, Haochen Shi, Hongtao Xue, Jie Hu, Shengdong Du, Tianrui Li, Xinyao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T03:56:46Z","title":"A Pre-trained Data Deduplication Model based on Active Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00721","kind":"arxiv","version":4},"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":"sha256:1f752a15cd33029e06e84fbf716a0c9dead96aea60ad985c84a1ace383b652ae","target":"record","created_at":"2026-07-05T09:59:12Z","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":"d4e0d99417003625bf2828cb64a807862563a3ca2946359af4953ffe628d3c48","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T03:56:46Z","title_canon_sha256":"e4ce088436cb294134b3bf0b84a8909793476872f67719d9d77d4ec9908bb63e"},"schema_version":"1.0","source":{"id":"2308.00721","kind":"arxiv","version":4}},"canonical_sha256":"683beefbd177af7d6cb9f3926130ad0cce31a15f24f781da3fc8614cad859935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"683beefbd177af7d6cb9f3926130ad0cce31a15f24f781da3fc8614cad859935","first_computed_at":"2026-07-05T09:59:12.312496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:12.312496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O9DMf60/0QdfRgawNHJv04tT/aAhfVRz06iXZXwK0vyjVxh8RUldSCB1ZZtK3cNLerBno5LWZmjci4qczoQPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:12.313075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.00721","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f752a15cd33029e06e84fbf716a0c9dead96aea60ad985c84a1ace383b652ae","sha256:6c6cc6190c021a5da0cf5c94ed298d81a1a12ad79131723f89c4862b51399016"],"state_sha256":"f4307cd4805308c3c58ae18e63519ed0d483ae1513de2db20db4d2ad7c0f6a03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nmgmsx/ctnD7nBIdNlTOnseyy95giEGnQxZr/SQj3OtNIkVgqM6jTMBs0fO2x1lHgP7dHAeUncJ3cl1cEIYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:52:51.929518Z","bundle_sha256":"3c9fdfcc9b1ba92a56160718fed241a17d84116198f1b252327050ac49917be8"}}