{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NC5H63PO7HZJ6WGJVSTP62VXXE","short_pith_number":"pith:NC5H63PO","canonical_record":{"source":{"id":"1906.08470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2019-06-20T07:21:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"aabb8b82152b3e43fcd7e0d3738f2ebd0e5073b03c3ed9d4809dc67bd8ea2e72","abstract_canon_sha256":"7cd2f4af0ba01d6f3015181ee82081717bfe46284a39db849795883cccb9d404"},"schema_version":"1.0"},"canonical_sha256":"68ba7f6deef9f29f58c9aca6ff6ab7b9086acc079772f412f6abc9a68c585a44","source":{"kind":"arxiv","id":"1906.08470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08470","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08470v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08470","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"NC5H63PO7HZJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NC5H63PO7HZJ6WGJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NC5H63PO","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NC5H63PO7HZJ6WGJVSTP62VXXE","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2019-06-20T07:21:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"aabb8b82152b3e43fcd7e0d3738f2ebd0e5073b03c3ed9d4809dc67bd8ea2e72","abstract_canon_sha256":"7cd2f4af0ba01d6f3015181ee82081717bfe46284a39db849795883cccb9d404"},"schema_version":"1.0"},"canonical_sha256":"68ba7f6deef9f29f58c9aca6ff6ab7b9086acc079772f412f6abc9a68c585a44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.395084Z","signature_b64":"p8086TLA0RZBJT2C53aB/q4PurXVhmrPcGOKpeGxVW5UdDpVxFMRfOJiCpmv1Sd+WHmrZ711iaqhEBpkHz5LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ba7f6deef9f29f58c9aca6ff6ab7b9086acc079772f412f6abc9a68c585a44","last_reissued_at":"2026-05-17T23:42:52.394574Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.394574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08470","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDukzZ/bICRMp4elWRmSOV73zSwIMjxlfoxkvfGAkIVwz097F7l+tHHBB1LUahdQqAPBqwXazjXadFjgEanxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:34:55.016651Z"},"content_sha256":"7ec3e43ea91176a15960fd2a356a3935dda49aed3f64768997ab0feb9897e9a1","schema_version":"1.0","event_id":"sha256:7ec3e43ea91176a15960fd2a356a3935dda49aed3f64768997ab0feb9897e9a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NC5H63PO7HZJ6WGJVSTP62VXXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cleaning Noisy and Heterogeneous Metadata for Record Linking Across Scholarly Big Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DL","authors_text":"Allen C. Ge, Athar Sefid, C. Lee Giles, Cornelia Caragea, Jian Wu, Jing Zhao, Lu Liu, Prasenjit Mitra","submitted_at":"2019-06-20T07:21:33Z","abstract_excerpt":"Automatically extracted metadata from scholarly documents in PDF formats is usually noisy and heterogeneous, often containing incomplete fields and erroneous values. One common way of cleaning metadata is to use a bibliographic reference dataset. The challenge is to match records between corpora with high precision. The existing solution which is based on information retrieval and string similarity on titles works well only if the titles are cleaned. We introduce a system designed to match scholarly document entities with noisy metadata against a reference dataset. The blocking function uses t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08470","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":""},"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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7c0NseSHvHnLsPudWkfCKZlhpzUXFo/9PmE0BS5aB70FsNrAt6OeYRDE0MsSGhMI88IEnrDqa+LxV9obnWjSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:34:55.017000Z"},"content_sha256":"749be06ca19414ef9d15fddef6790b3c9f19b82a148b1e158dcb543cfe060e42","schema_version":"1.0","event_id":"sha256:749be06ca19414ef9d15fddef6790b3c9f19b82a148b1e158dcb543cfe060e42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/bundle.json","state_url":"https://pith.science/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/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":"2026-06-02T05:34:55Z","links":{"resolver":"https://pith.science/pith/NC5H63PO7HZJ6WGJVSTP62VXXE","bundle":"https://pith.science/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/bundle.json","state":"https://pith.science/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NC5H63PO7HZJ6WGJVSTP62VXXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NC5H63PO7HZJ6WGJVSTP62VXXE","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":"7cd2f4af0ba01d6f3015181ee82081717bfe46284a39db849795883cccb9d404","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2019-06-20T07:21:33Z","title_canon_sha256":"aabb8b82152b3e43fcd7e0d3738f2ebd0e5073b03c3ed9d4809dc67bd8ea2e72"},"schema_version":"1.0","source":{"id":"1906.08470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08470","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08470v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08470","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"NC5H63PO7HZJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NC5H63PO7HZJ6WGJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NC5H63PO","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:749be06ca19414ef9d15fddef6790b3c9f19b82a148b1e158dcb543cfe060e42","target":"graph","created_at":"2026-05-17T23:42:52Z","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":"Automatically extracted metadata from scholarly documents in PDF formats is usually noisy and heterogeneous, often containing incomplete fields and erroneous values. One common way of cleaning metadata is to use a bibliographic reference dataset. The challenge is to match records between corpora with high precision. The existing solution which is based on information retrieval and string similarity on titles works well only if the titles are cleaned. We introduce a system designed to match scholarly document entities with noisy metadata against a reference dataset. The blocking function uses t","authors_text":"Allen C. Ge, Athar Sefid, C. Lee Giles, Cornelia Caragea, Jian Wu, Jing Zhao, Lu Liu, Prasenjit Mitra","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2019-06-20T07:21:33Z","title":"Cleaning Noisy and Heterogeneous Metadata for Record Linking Across Scholarly Big Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08470","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":"sha256:7ec3e43ea91176a15960fd2a356a3935dda49aed3f64768997ab0feb9897e9a1","target":"record","created_at":"2026-05-17T23:42:52Z","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":"7cd2f4af0ba01d6f3015181ee82081717bfe46284a39db849795883cccb9d404","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2019-06-20T07:21:33Z","title_canon_sha256":"aabb8b82152b3e43fcd7e0d3738f2ebd0e5073b03c3ed9d4809dc67bd8ea2e72"},"schema_version":"1.0","source":{"id":"1906.08470","kind":"arxiv","version":1}},"canonical_sha256":"68ba7f6deef9f29f58c9aca6ff6ab7b9086acc079772f412f6abc9a68c585a44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68ba7f6deef9f29f58c9aca6ff6ab7b9086acc079772f412f6abc9a68c585a44","first_computed_at":"2026-05-17T23:42:52.394574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:52.394574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8086TLA0RZBJT2C53aB/q4PurXVhmrPcGOKpeGxVW5UdDpVxFMRfOJiCpmv1Sd+WHmrZ711iaqhEBpkHz5LBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:52.395084Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec3e43ea91176a15960fd2a356a3935dda49aed3f64768997ab0feb9897e9a1","sha256:749be06ca19414ef9d15fddef6790b3c9f19b82a148b1e158dcb543cfe060e42"],"state_sha256":"8753e33f23e9b211f81d682764f3599b836186cbe88a8f7efcd9b03ad743a621"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BKpamxDAVuElZmlTQs87GrSFQpzsN9iTYYTX1F1H1NFjHWLqDusFwZYmBj11i0k4uqwdo6UzBKkyLEC07iN+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:34:55.019058Z","bundle_sha256":"a79aedddc5b774e3f9dff71334bb1de9089bcb991487ec9ed924a9e7d7016b34"}}