{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BXWELWL56HCXCMLSONCZNGUYOW","short_pith_number":"pith:BXWELWL5","canonical_record":{"source":{"id":"2006.10208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"efb0c223683cf8041f00823b4a039c06de45788b9ecfe23fa869f1a6dd8f155e","abstract_canon_sha256":"749b6e1c910dd65ff3ab9bec0faf97e1ae5fc2723b4356f86b055dc30e29cee3"},"schema_version":"1.0"},"canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","source":{"kind":"arxiv","id":"2006.10208","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10208","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10208v1","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10208","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_12","alias_value":"BXWELWL56HCX","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_16","alias_value":"BXWELWL56HCXCMLS","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_8","alias_value":"BXWELWL5","created_at":"2026-07-05T01:11:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BXWELWL56HCXCMLSONCZNGUYOW","target":"record","payload":{"canonical_record":{"source":{"id":"2006.10208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"efb0c223683cf8041f00823b4a039c06de45788b9ecfe23fa869f1a6dd8f155e","abstract_canon_sha256":"749b6e1c910dd65ff3ab9bec0faf97e1ae5fc2723b4356f86b055dc30e29cee3"},"schema_version":"1.0"},"canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:15.907812Z","signature_b64":"pYWDsUjzQt3sE84HE+iAuoZN3T0rocl1Kn4UPzOYhDYoMkAMQVMEnG2OktegJWGMYmw2+AQsOPzcyKZBGuUJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","last_reissued_at":"2026-07-05T01:11:15.907300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:15.907300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.10208","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":"2026-07-05T01:11:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHW1ER0Cmpo93yCC3J9IEBbILalBP4urxJcEkDjS0hbvmhMnb0rXjBtjBnb0cKs/C+H2K2mK51xkzu2TBL/fBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:20:25.255464Z"},"content_sha256":"783e379c7eae5b0259466ed9ea0c413b5304137b18b0b3977db9d4e1574fd1de","schema_version":"1.0","event_id":"sha256:783e379c7eae5b0259466ed9ea0c413b5304137b18b0b3977db9d4e1574fd1de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BXWELWL56HCXCMLSONCZNGUYOW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Record fusion: A learning approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Heidari, George Michalopoulos, Ihab F. Ilyas, Shrinu Kushagra, Theodoros Rekatsinas","submitted_at":"2020-06-18T00:04:37Z","abstract_excerpt":"Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the \"correct\" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database.\n  Our learning algorithm uses a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10208","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/2006.10208/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":"2026-07-05T01:11:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhVI2t4FryjsIoJ/ArFcvFQy5eXP2hxEyzMwUv6Jfr68Gb4aJxsaQjQa/nSwBhS9p9rhvMLR0q2PviIJiAc4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:20:25.255981Z"},"content_sha256":"6d95489487dd748bb4da4e325e1ffa968bc70e71f7bf60e3f41059849a0fc2c4","schema_version":"1.0","event_id":"sha256:6d95489487dd748bb4da4e325e1ffa968bc70e71f7bf60e3f41059849a0fc2c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/bundle.json","state_url":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXWELWL56HCXCMLSONCZNGUYOW/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":"2026-08-22T22:20:25Z","links":{"resolver":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW","bundle":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/bundle.json","state":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXWELWL56HCXCMLSONCZNGUYOW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BXWELWL56HCXCMLSONCZNGUYOW","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":"749b6e1c910dd65ff3ab9bec0faf97e1ae5fc2723b4356f86b055dc30e29cee3","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","title_canon_sha256":"efb0c223683cf8041f00823b4a039c06de45788b9ecfe23fa869f1a6dd8f155e"},"schema_version":"1.0","source":{"id":"2006.10208","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10208","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10208v1","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10208","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_12","alias_value":"BXWELWL56HCX","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_16","alias_value":"BXWELWL56HCXCMLS","created_at":"2026-07-05T01:11:15Z"},{"alias_kind":"pith_short_8","alias_value":"BXWELWL5","created_at":"2026-07-05T01:11:15Z"}],"graph_snapshots":[{"event_id":"sha256:6d95489487dd748bb4da4e325e1ffa968bc70e71f7bf60e3f41059849a0fc2c4","target":"graph","created_at":"2026-07-05T01:11:15Z","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/2006.10208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the \"correct\" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database.\n  Our learning algorithm uses a","authors_text":"Alireza Heidari, George Michalopoulos, Ihab F. Ilyas, Shrinu Kushagra, Theodoros Rekatsinas","cross_cats":["cs.DB","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","title":"Record fusion: A learning approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10208","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":"sha256:783e379c7eae5b0259466ed9ea0c413b5304137b18b0b3977db9d4e1574fd1de","target":"record","created_at":"2026-07-05T01:11:15Z","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":"749b6e1c910dd65ff3ab9bec0faf97e1ae5fc2723b4356f86b055dc30e29cee3","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","title_canon_sha256":"efb0c223683cf8041f00823b4a039c06de45788b9ecfe23fa869f1a6dd8f155e"},"schema_version":"1.0","source":{"id":"2006.10208","kind":"arxiv","version":1}},"canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","first_computed_at":"2026-07-05T01:11:15.907300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:15.907300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pYWDsUjzQt3sE84HE+iAuoZN3T0rocl1Kn4UPzOYhDYoMkAMQVMEnG2OktegJWGMYmw2+AQsOPzcyKZBGuUJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:15.907812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10208","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:783e379c7eae5b0259466ed9ea0c413b5304137b18b0b3977db9d4e1574fd1de","sha256:6d95489487dd748bb4da4e325e1ffa968bc70e71f7bf60e3f41059849a0fc2c4"],"state_sha256":"70fa70befc795235176867e4491323e85e916d2d9a7de1bdc5fe851c8d794ec3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3apwCwCHB5t6frwfnxU7cmxY3YsN2g+s2sR/3PhIWPKoYFIWSGbEsOBtGDo0agzdeiduPuxQiuy3NtLTf/geAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:20:25.259874Z","bundle_sha256":"c9edfd3f2f5bf526554e53b726734ac75df07876ce54937466a33961a424c178"}}