{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BETXZC6LVHOLHBVCTWE6RGBM3D","short_pith_number":"pith:BETXZC6L","canonical_record":{"source":{"id":"2407.12802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-06-24T04:16:32Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"ecfb0ac3c97dcb407b3f958ef9cbd26164632053d7af0f7c55a3d94582fa6481","abstract_canon_sha256":"ba3746e578da8c3d712e4d3b30f9e4ef04d27f278cde46f387c21a068e150c6f"},"schema_version":"1.0"},"canonical_sha256":"09277c8bcba9dcb386a29d89e8982cd8e3c2c64a6bd35c26a0f874ef62bb9d00","source":{"kind":"arxiv","id":"2407.12802","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12802","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12802v1","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12802","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"BETXZC6LVHOL","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"BETXZC6LVHOLHBVC","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"BETXZC6L","created_at":"2026-07-05T08:45:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BETXZC6LVHOLHBVCTWE6RGBM3D","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-06-24T04:16:32Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"ecfb0ac3c97dcb407b3f958ef9cbd26164632053d7af0f7c55a3d94582fa6481","abstract_canon_sha256":"ba3746e578da8c3d712e4d3b30f9e4ef04d27f278cde46f387c21a068e150c6f"},"schema_version":"1.0"},"canonical_sha256":"09277c8bcba9dcb386a29d89e8982cd8e3c2c64a6bd35c26a0f874ef62bb9d00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:11.640071Z","signature_b64":"ZKrXcuT3wAnMIYwwSBc+S1eDVmgJ8PyaXzLca5CMa5owUEqujNJ0WryLP+i5zSwU4xSOyYZcDCKA61D9GTIZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09277c8bcba9dcb386a29d89e8982cd8e3c2c64a6bd35c26a0f874ef62bb9d00","last_reissued_at":"2026-07-05T08:45:11.639726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:11.639726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12802","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":"2026-07-05T08:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iExd4vSg5mT6eNO/lpGnmABg/jAYQ717ddG1R3kEmve1WIp9nY8CO/T+oKbVf7JJlfZESuEwZYGP63aPXColCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:15.877347Z"},"content_sha256":"42a1c38a964b9a4882cab568676249ea3e66d6a8469c3efadab3f975a9e71c74","schema_version":"1.0","event_id":"sha256:42a1c38a964b9a4882cab568676249ea3e66d6a8469c3efadab3f975a9e71c74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BETXZC6LVHOLHBVCTWE6RGBM3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimClone: Detecting Tabular Data Clones using Value Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.DB","authors_text":"Dayi Lin, Gopi Krishnan Rajbahadur, Shaowei Wang, Xu Yang, Zhen Ming (Jack) Jiang","submitted_at":"2024-06-24T04:16:32Z","abstract_excerpt":"Data clones are defined as multiple copies of the same data among datasets. Presence of data clones between datasets can cause issues such as difficulties in managing data assets and data license violations when using datasets with clones to build AI software. However, detecting data clones is not trivial. Majority of the prior studies in this area rely on structural information to detect data clones (e.g., font size, column header). However, tabular datasets used to build AI software are typically stored without any structural information. In this paper, we propose a novel method called SimCl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12802","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/2407.12802/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":"2026-07-05T08:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"whIBU5XCGUdot9Ndvwyl2412LAXtBEMDPhP7BTun3QccUV+VGDll2d7NTPklfTfNlw0t8IAcmII7k0lhVlOsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:15.877727Z"},"content_sha256":"8a80dbcfb818ad9b0d7412158df12b9a8ca3d506db75f5f2eb9207485678d504","schema_version":"1.0","event_id":"sha256:8a80dbcfb818ad9b0d7412158df12b9a8ca3d506db75f5f2eb9207485678d504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/bundle.json","state_url":"https://pith.science/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/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":"2026-07-06T18:44:15Z","links":{"resolver":"https://pith.science/pith/BETXZC6LVHOLHBVCTWE6RGBM3D","bundle":"https://pith.science/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/bundle.json","state":"https://pith.science/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BETXZC6LVHOLHBVCTWE6RGBM3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BETXZC6LVHOLHBVCTWE6RGBM3D","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":"ba3746e578da8c3d712e4d3b30f9e4ef04d27f278cde46f387c21a068e150c6f","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-06-24T04:16:32Z","title_canon_sha256":"ecfb0ac3c97dcb407b3f958ef9cbd26164632053d7af0f7c55a3d94582fa6481"},"schema_version":"1.0","source":{"id":"2407.12802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12802","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12802v1","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12802","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"BETXZC6LVHOL","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"BETXZC6LVHOLHBVC","created_at":"2026-07-05T08:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"BETXZC6L","created_at":"2026-07-05T08:45:11Z"}],"graph_snapshots":[{"event_id":"sha256:8a80dbcfb818ad9b0d7412158df12b9a8ca3d506db75f5f2eb9207485678d504","target":"graph","created_at":"2026-07-05T08:45:11Z","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/2407.12802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data clones are defined as multiple copies of the same data among datasets. Presence of data clones between datasets can cause issues such as difficulties in managing data assets and data license violations when using datasets with clones to build AI software. However, detecting data clones is not trivial. Majority of the prior studies in this area rely on structural information to detect data clones (e.g., font size, column header). However, tabular datasets used to build AI software are typically stored without any structural information. In this paper, we propose a novel method called SimCl","authors_text":"Dayi Lin, Gopi Krishnan Rajbahadur, Shaowei Wang, Xu Yang, Zhen Ming (Jack) Jiang","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-06-24T04:16:32Z","title":"SimClone: Detecting Tabular Data Clones using Value Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12802","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":"sha256:42a1c38a964b9a4882cab568676249ea3e66d6a8469c3efadab3f975a9e71c74","target":"record","created_at":"2026-07-05T08:45:11Z","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":"ba3746e578da8c3d712e4d3b30f9e4ef04d27f278cde46f387c21a068e150c6f","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-06-24T04:16:32Z","title_canon_sha256":"ecfb0ac3c97dcb407b3f958ef9cbd26164632053d7af0f7c55a3d94582fa6481"},"schema_version":"1.0","source":{"id":"2407.12802","kind":"arxiv","version":1}},"canonical_sha256":"09277c8bcba9dcb386a29d89e8982cd8e3c2c64a6bd35c26a0f874ef62bb9d00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09277c8bcba9dcb386a29d89e8982cd8e3c2c64a6bd35c26a0f874ef62bb9d00","first_computed_at":"2026-07-05T08:45:11.639726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:11.639726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZKrXcuT3wAnMIYwwSBc+S1eDVmgJ8PyaXzLca5CMa5owUEqujNJ0WryLP+i5zSwU4xSOyYZcDCKA61D9GTIZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:11.640071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a1c38a964b9a4882cab568676249ea3e66d6a8469c3efadab3f975a9e71c74","sha256:8a80dbcfb818ad9b0d7412158df12b9a8ca3d506db75f5f2eb9207485678d504"],"state_sha256":"a8e12521e1e11a64bb5447dbe8e44eeb039e0917a99c544d8c4fecb37c2bf4db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wobwhsFOu0AenvuYABv5zkwvEp/cKXlDRLYFH75i9Mur1MsKrNYnsWGS867kcS+K8SJx4M3WJVjP16ILNjAgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:44:15.879710Z","bundle_sha256":"a4177326f6c2bfe60b4bd373f446b6fe7849e984b3fc8fb74a1e979bf027d4f9"}}