{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LTUFDG2SULKPTP573UFNXUMWYO","short_pith_number":"pith:LTUFDG2S","canonical_record":{"source":{"id":"2205.05889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T05:50:30Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"ef7f3d54e0dcff44fd2ac319ddee093e6063138d7f50c08f9d84313e55a8d293","abstract_canon_sha256":"f8d3af2a6f99579919e06fb73602675c895412c078b737c6e29ad0ce9ff9803e"},"schema_version":"1.0"},"canonical_sha256":"5ce8519b52a2d4f9bfbfdd0adbd196c389a36ff52c2ee4f4ab64b7f10e22069e","source":{"kind":"arxiv","id":"2205.05889","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05889","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05889v1","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05889","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"LTUFDG2SULKP","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"LTUFDG2SULKPTP57","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"LTUFDG2S","created_at":"2026-07-05T04:22:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LTUFDG2SULKPTP573UFNXUMWYO","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T05:50:30Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"ef7f3d54e0dcff44fd2ac319ddee093e6063138d7f50c08f9d84313e55a8d293","abstract_canon_sha256":"f8d3af2a6f99579919e06fb73602675c895412c078b737c6e29ad0ce9ff9803e"},"schema_version":"1.0"},"canonical_sha256":"5ce8519b52a2d4f9bfbfdd0adbd196c389a36ff52c2ee4f4ab64b7f10e22069e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:43.181901Z","signature_b64":"I2G5dZmuc/zd+4hWRq85YVvWe6Ve6RriBhqys+6fDRY0YG3BRbPcscDktEN/wwWktkdzlm2UMhsm++RyjphxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce8519b52a2d4f9bfbfdd0adbd196c389a36ff52c2ee4f4ab64b7f10e22069e","last_reissued_at":"2026-07-05T04:22:43.181417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:43.181417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05889","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":"2026-07-05T04:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YGNKzOfRwkbAsSNGTTM38P/GBJKNIrQIjB677siHyEmeJOiB5QjbJ/5thMK1XXouLr5pR2ouUixt9oQET848Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:58.596652Z"},"content_sha256":"ef4ced83efb3bc15ba21b0f096b230d7e4bfadf912c45553c5e842da06e865ed","schema_version":"1.0","event_id":"sha256:ef4ced83efb3bc15ba21b0f096b230d7e4bfadf912c45553c5e842da06e865ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LTUFDG2SULKPTP573UFNXUMWYO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Cheng Fu, Feiyu Xiong, Hongyu Lin, Hui Chen, Le Sun, Minlong Lu, Tianshu Wang, Xianpei Han, Xiuwen Zhu","submitted_at":"2022-05-12T05:50:30Z","abstract_excerpt":"Entity matching (EM) is the most critical step for entity resolution (ER). While current deep learningbased methods achieve very impressive performance on standard EM benchmarks, their realworld application performance is much frustrating. In this paper, we highlight that such the gap between reality and ideality stems from the unreasonable benchmark construction process, which is inconsistent with the nature of entity matching and therefore leads to biased evaluations of current EM approaches. To this end, we build a new EM corpus and re-construct EM benchmarks to challenge critical assumptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05889","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/2205.05889/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":"2026-07-05T04:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GN5Wu0ViQl/4pdZzFdLNs93h34tfl+5P6IkhVvi3f7qbRNEbqyxAz2cu1g0pKs228ry2NlOhkmEoqL/S5pKhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:58.597033Z"},"content_sha256":"c2026d5bfdeadd0a334ec4d1853d26d5b5efef568212c52cef299eb8f8b5858b","schema_version":"1.0","event_id":"sha256:c2026d5bfdeadd0a334ec4d1853d26d5b5efef568212c52cef299eb8f8b5858b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTUFDG2SULKPTP573UFNXUMWYO/bundle.json","state_url":"https://pith.science/pith/LTUFDG2SULKPTP573UFNXUMWYO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTUFDG2SULKPTP573UFNXUMWYO/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":"2026-08-04T00:30:58Z","links":{"resolver":"https://pith.science/pith/LTUFDG2SULKPTP573UFNXUMWYO","bundle":"https://pith.science/pith/LTUFDG2SULKPTP573UFNXUMWYO/bundle.json","state":"https://pith.science/pith/LTUFDG2SULKPTP573UFNXUMWYO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTUFDG2SULKPTP573UFNXUMWYO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LTUFDG2SULKPTP573UFNXUMWYO","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":"f8d3af2a6f99579919e06fb73602675c895412c078b737c6e29ad0ce9ff9803e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T05:50:30Z","title_canon_sha256":"ef7f3d54e0dcff44fd2ac319ddee093e6063138d7f50c08f9d84313e55a8d293"},"schema_version":"1.0","source":{"id":"2205.05889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05889","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05889v1","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05889","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"LTUFDG2SULKP","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"LTUFDG2SULKPTP57","created_at":"2026-07-05T04:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"LTUFDG2S","created_at":"2026-07-05T04:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:c2026d5bfdeadd0a334ec4d1853d26d5b5efef568212c52cef299eb8f8b5858b","target":"graph","created_at":"2026-07-05T04:22:43Z","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/2205.05889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity matching (EM) is the most critical step for entity resolution (ER). While current deep learningbased methods achieve very impressive performance on standard EM benchmarks, their realworld application performance is much frustrating. In this paper, we highlight that such the gap between reality and ideality stems from the unreasonable benchmark construction process, which is inconsistent with the nature of entity matching and therefore leads to biased evaluations of current EM approaches. To this end, we build a new EM corpus and re-construct EM benchmarks to challenge critical assumptio","authors_text":"Cheng Fu, Feiyu Xiong, Hongyu Lin, Hui Chen, Le Sun, Minlong Lu, Tianshu Wang, Xianpei Han, Xiuwen Zhu","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T05:50:30Z","title":"Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05889","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:ef4ced83efb3bc15ba21b0f096b230d7e4bfadf912c45553c5e842da06e865ed","target":"record","created_at":"2026-07-05T04:22:43Z","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":"f8d3af2a6f99579919e06fb73602675c895412c078b737c6e29ad0ce9ff9803e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T05:50:30Z","title_canon_sha256":"ef7f3d54e0dcff44fd2ac319ddee093e6063138d7f50c08f9d84313e55a8d293"},"schema_version":"1.0","source":{"id":"2205.05889","kind":"arxiv","version":1}},"canonical_sha256":"5ce8519b52a2d4f9bfbfdd0adbd196c389a36ff52c2ee4f4ab64b7f10e22069e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ce8519b52a2d4f9bfbfdd0adbd196c389a36ff52c2ee4f4ab64b7f10e22069e","first_computed_at":"2026-07-05T04:22:43.181417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:43.181417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I2G5dZmuc/zd+4hWRq85YVvWe6Ve6RriBhqys+6fDRY0YG3BRbPcscDktEN/wwWktkdzlm2UMhsm++RyjphxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:43.181901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef4ced83efb3bc15ba21b0f096b230d7e4bfadf912c45553c5e842da06e865ed","sha256:c2026d5bfdeadd0a334ec4d1853d26d5b5efef568212c52cef299eb8f8b5858b"],"state_sha256":"ddbfe6f34dbd0ad7f189406985343032d0167ccd2b1858d87da63112db77d9c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EKx1QrKAVXpQnzdv2b7Wt/bR907+sqYymm9XxI6l5lLIt+hnIWWoz49HHW7hkRmyBBKdkh0eijaOLrBeULSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:30:58.599691Z","bundle_sha256":"0dec984534da62ea53314baa9e5fdf3b51de83dfaf1ae35a51713820c48a3047"}}