{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7BVIAMFHV32UO6LBBGQMVYN4YG","short_pith_number":"pith:7BVIAMFH","canonical_record":{"source":{"id":"2307.01231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-07-03T07:54:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1db9a07871ff8b55593547b0ead10151ba6c4d87df62b0422c3e089be1d60c7c","abstract_canon_sha256":"3b56afc78690f2f923d444697ce9b9b3bcea5c674e00e8527f02cac719138fe5"},"schema_version":"1.0"},"canonical_sha256":"f86a8030a7aef547796109a0cae1bcc1b046a33758f96b66e94806ab58479438","source":{"kind":"arxiv","id":"2307.01231","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01231","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01231v2","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01231","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"7BVIAMFHV32U","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"7BVIAMFHV32UO6LB","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"7BVIAMFH","created_at":"2026-07-05T07:11:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7BVIAMFHV32UO6LBBGQMVYN4YG","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-07-03T07:54:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1db9a07871ff8b55593547b0ead10151ba6c4d87df62b0422c3e089be1d60c7c","abstract_canon_sha256":"3b56afc78690f2f923d444697ce9b9b3bcea5c674e00e8527f02cac719138fe5"},"schema_version":"1.0"},"canonical_sha256":"f86a8030a7aef547796109a0cae1bcc1b046a33758f96b66e94806ab58479438","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:57.236736Z","signature_b64":"WLwBTM2VIJEnRKyL1Iu42qwfgDnMccY+MPep6kd59Fk2hmKwgyzOratK4SSBSOBYTY3hwSzoGrGMg6DVjbwpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f86a8030a7aef547796109a0cae1bcc1b046a33758f96b66e94806ab58479438","last_reissued_at":"2026-07-05T07:11:57.236254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:57.236254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01231","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SkfIkCHd90Q+C7HZAvd+d55jvwG6XwGAWB4tCBzIKW5/rtqxhCPR2nmFRiDcH73sDXnqh2etBv24R0rD7LVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:10:01.560273Z"},"content_sha256":"d003806735f72b944c68faf68f33e4b0fcd7431ef85423db24989684a9975e64","schema_version":"1.0","event_id":"sha256:d003806735f72b944c68faf68f33e4b0fcd7431ef85423db24989684a9975e64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7BVIAMFHV32UO6LBBGQMVYN4YG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Critical Re-evaluation of Benchmark Datasets for (Deep) Learning-Based Matching Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"George Papadakis, Nishadi Kirielle, Peter Christen, Themis Palpanas","submitted_at":"2023-07-03T07:54:54Z","abstract_excerpt":"Entity resolution (ER) is the process of identifying records that refer to the same entities within one or across multiple databases. Numerous techniques have been developed to tackle ER challenges over the years, with recent emphasis placed on machine and deep learning methods for the matching phase. However, the quality of the benchmark datasets typically used in the experimental evaluations of learning-based matching algorithms has not been examined in the literature. To cover this gap, we propose four different approaches to assessing the difficulty and appropriateness of 13 established da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01231","kind":"arxiv","version":2},"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/2307.01231/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":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUK+Prc2LsU5gMbxd5gMtUO+qYS58G2LuKH9zSYREmpJVnKS5Ir/CH+1Xllh/vdyJ20KgD/6S0pbpF3zUxynCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:10:01.561011Z"},"content_sha256":"4370a89d35f1a1d326456946b8d61fe2a30ab6f48c095e865ea1b131c390b1e9","schema_version":"1.0","event_id":"sha256:4370a89d35f1a1d326456946b8d61fe2a30ab6f48c095e865ea1b131c390b1e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/bundle.json","state_url":"https://pith.science/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/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":"2026-08-09T14:10:01Z","links":{"resolver":"https://pith.science/pith/7BVIAMFHV32UO6LBBGQMVYN4YG","bundle":"https://pith.science/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/bundle.json","state":"https://pith.science/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BVIAMFHV32UO6LBBGQMVYN4YG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7BVIAMFHV32UO6LBBGQMVYN4YG","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":"3b56afc78690f2f923d444697ce9b9b3bcea5c674e00e8527f02cac719138fe5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-07-03T07:54:54Z","title_canon_sha256":"1db9a07871ff8b55593547b0ead10151ba6c4d87df62b0422c3e089be1d60c7c"},"schema_version":"1.0","source":{"id":"2307.01231","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01231","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01231v2","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01231","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"7BVIAMFHV32U","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"7BVIAMFHV32UO6LB","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"7BVIAMFH","created_at":"2026-07-05T07:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:4370a89d35f1a1d326456946b8d61fe2a30ab6f48c095e865ea1b131c390b1e9","target":"graph","created_at":"2026-07-05T07:11:57Z","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/2307.01231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity resolution (ER) is the process of identifying records that refer to the same entities within one or across multiple databases. Numerous techniques have been developed to tackle ER challenges over the years, with recent emphasis placed on machine and deep learning methods for the matching phase. However, the quality of the benchmark datasets typically used in the experimental evaluations of learning-based matching algorithms has not been examined in the literature. To cover this gap, we propose four different approaches to assessing the difficulty and appropriateness of 13 established da","authors_text":"George Papadakis, Nishadi Kirielle, Peter Christen, Themis Palpanas","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-07-03T07:54:54Z","title":"A Critical Re-evaluation of Benchmark Datasets for (Deep) Learning-Based Matching Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01231","kind":"arxiv","version":2},"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:d003806735f72b944c68faf68f33e4b0fcd7431ef85423db24989684a9975e64","target":"record","created_at":"2026-07-05T07:11:57Z","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":"3b56afc78690f2f923d444697ce9b9b3bcea5c674e00e8527f02cac719138fe5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-07-03T07:54:54Z","title_canon_sha256":"1db9a07871ff8b55593547b0ead10151ba6c4d87df62b0422c3e089be1d60c7c"},"schema_version":"1.0","source":{"id":"2307.01231","kind":"arxiv","version":2}},"canonical_sha256":"f86a8030a7aef547796109a0cae1bcc1b046a33758f96b66e94806ab58479438","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f86a8030a7aef547796109a0cae1bcc1b046a33758f96b66e94806ab58479438","first_computed_at":"2026-07-05T07:11:57.236254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:57.236254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLwBTM2VIJEnRKyL1Iu42qwfgDnMccY+MPep6kd59Fk2hmKwgyzOratK4SSBSOBYTY3hwSzoGrGMg6DVjbwpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:57.236736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01231","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d003806735f72b944c68faf68f33e4b0fcd7431ef85423db24989684a9975e64","sha256:4370a89d35f1a1d326456946b8d61fe2a30ab6f48c095e865ea1b131c390b1e9"],"state_sha256":"bf05b8416c92403b3b10861a56cbe64fc17811be7f64aa841a69672c27e65a19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XVTbgG8ElsLjs0jC6nGmalcFyqv+7TtXKWazVlT9+X4jGdF06S4YmFY3eaVDLgNNClnhVsFCeRFEJ6yaSBtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:10:01.567545Z","bundle_sha256":"04dfaf8246f0b50434b3bc2442165f90ae2ab54a2db84f95b188ff519932d138"}}