{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5J655RV5WQSK67XUHTFFV52BON","short_pith_number":"pith:5J655RV5","canonical_record":{"source":{"id":"1609.06265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-20T17:44:28Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"5e07829bb852c22b7a6755479c530b37da4cc2a50eee5000a560e2216c5bae54","abstract_canon_sha256":"390588ac5cae1753f0091c242a36377a2b449451dfcf4e3ac159c4a772810721"},"schema_version":"1.0"},"canonical_sha256":"ea7ddec6bdb424af7ef43cca5af741735af4f779a5e214ba6b269d9d495ac013","source":{"kind":"arxiv","id":"1609.06265","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06265","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06265v2","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06265","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"5J655RV5WQSK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5J655RV5WQSK67XU","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5J655RV5","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5J655RV5WQSK67XUHTFFV52BON","target":"record","payload":{"canonical_record":{"source":{"id":"1609.06265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-20T17:44:28Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"5e07829bb852c22b7a6755479c530b37da4cc2a50eee5000a560e2216c5bae54","abstract_canon_sha256":"390588ac5cae1753f0091c242a36377a2b449451dfcf4e3ac159c4a772810721"},"schema_version":"1.0"},"canonical_sha256":"ea7ddec6bdb424af7ef43cca5af741735af4f779a5e214ba6b269d9d495ac013","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:08.618419Z","signature_b64":"rbotVCmjefgYFT9kKRZ7TsiiIfr+Bi/V8XPaaqB3Fzch5jRFeTh6MWFMOn3AqtepRAOS5H/0cuex3O5gYjh3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea7ddec6bdb424af7ef43cca5af741735af4f779a5e214ba6b269d9d495ac013","last_reissued_at":"2026-05-18T01:04:08.617868Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:08.617868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.06265","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":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IHfTAHAa33fxqbFgTy44gu2ncQxPjq5u+rRgb9V7BkjgLHxcwa0/5sGNou2BMEjP+/+7wHZs6dSA21FQAIuWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:18:38.799252Z"},"content_sha256":"26e796e6a31926065367661aea02d69678f78d79bda377557e6f051b1816d8eb","schema_version":"1.0","event_id":"sha256:26e796e6a31926065367661aea02d69678f78d79bda377557e6f051b1816d8eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5J655RV5WQSK67XUHTFFV52BON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Ensemble Blocking Scheme for Entity Resolution of Large and Sparse Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Chris Min, Faizan Javed, Janani Balaji, Mayank Kejriwal, Ozgur Ozturk, Sam Sander","submitted_at":"2016-09-20T17:44:28Z","abstract_excerpt":"Entity Resolution, also called record linkage or deduplication, refers to the process of identifying and merging duplicate versions of the same entity into a unified representation. The standard practice is to use a Rule based or Machine Learning based model that compares entity pairs and assigns a score to represent the pairs' Match/Non-Match status. However, performing an exhaustive pair-wise comparison on all pairs of records leads to quadratic matcher complexity and hence a Blocking step is performed before the Matching to group similar entities into smaller blocks that the matcher can the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06265","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":""},"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":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/fmJ4OjQ+62+WbIUUQ2R4FLpuUlDmDJuZqTW2NOzrX9k0wBUSqGVi7Mz7Cdcazl9Tc2saYvqB24Iw/bCFNBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:18:38.800022Z"},"content_sha256":"1657de7e4d3cffc7b0487aa1d72383026082227f14cd2366bfa09f1db872063e","schema_version":"1.0","event_id":"sha256:1657de7e4d3cffc7b0487aa1d72383026082227f14cd2366bfa09f1db872063e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J655RV5WQSK67XUHTFFV52BON/bundle.json","state_url":"https://pith.science/pith/5J655RV5WQSK67XUHTFFV52BON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J655RV5WQSK67XUHTFFV52BON/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":"2026-06-11T17:18:38Z","links":{"resolver":"https://pith.science/pith/5J655RV5WQSK67XUHTFFV52BON","bundle":"https://pith.science/pith/5J655RV5WQSK67XUHTFFV52BON/bundle.json","state":"https://pith.science/pith/5J655RV5WQSK67XUHTFFV52BON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J655RV5WQSK67XUHTFFV52BON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5J655RV5WQSK67XUHTFFV52BON","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":"390588ac5cae1753f0091c242a36377a2b449451dfcf4e3ac159c4a772810721","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-20T17:44:28Z","title_canon_sha256":"5e07829bb852c22b7a6755479c530b37da4cc2a50eee5000a560e2216c5bae54"},"schema_version":"1.0","source":{"id":"1609.06265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06265","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06265v2","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06265","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"5J655RV5WQSK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5J655RV5WQSK67XU","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5J655RV5","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:1657de7e4d3cffc7b0487aa1d72383026082227f14cd2366bfa09f1db872063e","target":"graph","created_at":"2026-05-18T01:04:08Z","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"},"paper":{"abstract_excerpt":"Entity Resolution, also called record linkage or deduplication, refers to the process of identifying and merging duplicate versions of the same entity into a unified representation. The standard practice is to use a Rule based or Machine Learning based model that compares entity pairs and assigns a score to represent the pairs' Match/Non-Match status. However, performing an exhaustive pair-wise comparison on all pairs of records leads to quadratic matcher complexity and hence a Blocking step is performed before the Matching to group similar entities into smaller blocks that the matcher can the","authors_text":"Chris Min, Faizan Javed, Janani Balaji, Mayank Kejriwal, Ozgur Ozturk, Sam Sander","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-20T17:44:28Z","title":"An Ensemble Blocking Scheme for Entity Resolution of Large and Sparse Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06265","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":"sha256:26e796e6a31926065367661aea02d69678f78d79bda377557e6f051b1816d8eb","target":"record","created_at":"2026-05-18T01:04:08Z","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":"390588ac5cae1753f0091c242a36377a2b449451dfcf4e3ac159c4a772810721","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-20T17:44:28Z","title_canon_sha256":"5e07829bb852c22b7a6755479c530b37da4cc2a50eee5000a560e2216c5bae54"},"schema_version":"1.0","source":{"id":"1609.06265","kind":"arxiv","version":2}},"canonical_sha256":"ea7ddec6bdb424af7ef43cca5af741735af4f779a5e214ba6b269d9d495ac013","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea7ddec6bdb424af7ef43cca5af741735af4f779a5e214ba6b269d9d495ac013","first_computed_at":"2026-05-18T01:04:08.617868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:08.617868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rbotVCmjefgYFT9kKRZ7TsiiIfr+Bi/V8XPaaqB3Fzch5jRFeTh6MWFMOn3AqtepRAOS5H/0cuex3O5gYjh3DA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:08.618419Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.06265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e796e6a31926065367661aea02d69678f78d79bda377557e6f051b1816d8eb","sha256:1657de7e4d3cffc7b0487aa1d72383026082227f14cd2366bfa09f1db872063e"],"state_sha256":"0e29a3d4980cb6d3127c941117d68353bac08645b8440f5021ea72eb6b29ae39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bJ8utdr3qDRTBBLeGb39PU4dq0uItGJyy9lRLMre38xFj6QDvP0NiJTU6RwVx9gmZFmU6Ey91J9aRuS455HBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T17:18:38.802500Z","bundle_sha256":"c8473ce1e449185c9c17ba40d74e1843885c3c8c192c1ee8bf8a1d40637382c6"}}