{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PEBBRFRSGHP5W2YDPUVFLGZP3N","short_pith_number":"pith:PEBBRFRS","canonical_record":{"source":{"id":"1712.06223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-18T01:57:39Z","cross_cats_sorted":[],"title_canon_sha256":"41a31f3eabc3116b2e4ed62ae19dd05b956194850162f0140d77b906e032fced","abstract_canon_sha256":"c06595c56b95ce71569f38a6be1fed07fe858e0c15d92a971d716fe0bcb015ef"},"schema_version":"1.0"},"canonical_sha256":"790218963231dfdb6b037d2a559b2fdb445666b07faa082149e59dc8e1c0d885","source":{"kind":"arxiv","id":"1712.06223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06223","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06223v1","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06223","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"PEBBRFRSGHP5","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEBBRFRSGHP5W2YD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEBBRFRS","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PEBBRFRSGHP5W2YDPUVFLGZP3N","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-18T01:57:39Z","cross_cats_sorted":[],"title_canon_sha256":"41a31f3eabc3116b2e4ed62ae19dd05b956194850162f0140d77b906e032fced","abstract_canon_sha256":"c06595c56b95ce71569f38a6be1fed07fe858e0c15d92a971d716fe0bcb015ef"},"schema_version":"1.0"},"canonical_sha256":"790218963231dfdb6b037d2a559b2fdb445666b07faa082149e59dc8e1c0d885","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:50.814080Z","signature_b64":"15eval3faMRgBj8ch9kvQEaR5XR/pBewOKeZ5STbxk/2Nb3+3JThZJfYmWmJicwwioZqDcJk2N8HCM5DdrIsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"790218963231dfdb6b037d2a559b2fdb445666b07faa082149e59dc8e1c0d885","last_reissued_at":"2026-05-18T00:27:50.813511Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:50.813511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06223","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":"2026-05-18T00:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Na7ewS56bKegcWHwE0jv1Esj3vNmZVlTYKgrx75se8ywqmaULf/TpCYHA4rZ64VhFOUHaerSFnhHDRE0xpouBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:57:51.329229Z"},"content_sha256":"e277a94e318281260cc94f8bd7705ac1e7ca4bb23e81108bf2b5dfded0c98b66","schema_version":"1.0","event_id":"sha256:e277a94e318281260cc94f8bd7705ac1e7ca4bb23e81108bf2b5dfded0c98b66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PEBBRFRSGHP5W2YDPUVFLGZP3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Error-Tolerant Big Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dong Deng","submitted_at":"2017-12-18T01:57:39Z","abstract_excerpt":"Real-world data contains various kinds of errors. Before analyzing data, one usually needs to process the raw data. However, traditional data processing based on exactly match often misses lots of valid information. To get high-quality analysis results and fit in the big data era, this thesis studies the error-tolerant big data processing. As most of the data in real world can be represented as a sequence or a set, this thesis utilizes the widely-used sequence-based and set-based similar functions to tolerate errors in data processing and studies the approximate entity extraction, similarity j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06223","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":"2026-05-18T00:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dn4blcpkNUAd7RTtpwzXJnY8bo8KFclmc3aAwAPI+FCu9rcU+/BY4yfjz1J3U+Kn3BHcTN5uuRvjQ2MbwC9AAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:57:51.329593Z"},"content_sha256":"54a6bfd93d6bae8aebbd109a83eaa611e27aa073053d02b90d1a0e3d3a86c61a","schema_version":"1.0","event_id":"sha256:54a6bfd93d6bae8aebbd109a83eaa611e27aa073053d02b90d1a0e3d3a86c61a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/bundle.json","state_url":"https://pith.science/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/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":"2026-06-03T08:57:51Z","links":{"resolver":"https://pith.science/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N","bundle":"https://pith.science/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/bundle.json","state":"https://pith.science/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEBBRFRSGHP5W2YDPUVFLGZP3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PEBBRFRSGHP5W2YDPUVFLGZP3N","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":"c06595c56b95ce71569f38a6be1fed07fe858e0c15d92a971d716fe0bcb015ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-18T01:57:39Z","title_canon_sha256":"41a31f3eabc3116b2e4ed62ae19dd05b956194850162f0140d77b906e032fced"},"schema_version":"1.0","source":{"id":"1712.06223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06223","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06223v1","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06223","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"PEBBRFRSGHP5","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEBBRFRSGHP5W2YD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEBBRFRS","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:54a6bfd93d6bae8aebbd109a83eaa611e27aa073053d02b90d1a0e3d3a86c61a","target":"graph","created_at":"2026-05-18T00:27:50Z","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":"Real-world data contains various kinds of errors. Before analyzing data, one usually needs to process the raw data. However, traditional data processing based on exactly match often misses lots of valid information. To get high-quality analysis results and fit in the big data era, this thesis studies the error-tolerant big data processing. As most of the data in real world can be represented as a sequence or a set, this thesis utilizes the widely-used sequence-based and set-based similar functions to tolerate errors in data processing and studies the approximate entity extraction, similarity j","authors_text":"Dong Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-18T01:57:39Z","title":"Error-Tolerant Big Data Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06223","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:e277a94e318281260cc94f8bd7705ac1e7ca4bb23e81108bf2b5dfded0c98b66","target":"record","created_at":"2026-05-18T00:27:50Z","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":"c06595c56b95ce71569f38a6be1fed07fe858e0c15d92a971d716fe0bcb015ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-18T01:57:39Z","title_canon_sha256":"41a31f3eabc3116b2e4ed62ae19dd05b956194850162f0140d77b906e032fced"},"schema_version":"1.0","source":{"id":"1712.06223","kind":"arxiv","version":1}},"canonical_sha256":"790218963231dfdb6b037d2a559b2fdb445666b07faa082149e59dc8e1c0d885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"790218963231dfdb6b037d2a559b2fdb445666b07faa082149e59dc8e1c0d885","first_computed_at":"2026-05-18T00:27:50.813511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:50.813511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15eval3faMRgBj8ch9kvQEaR5XR/pBewOKeZ5STbxk/2Nb3+3JThZJfYmWmJicwwioZqDcJk2N8HCM5DdrIsCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:50.814080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e277a94e318281260cc94f8bd7705ac1e7ca4bb23e81108bf2b5dfded0c98b66","sha256:54a6bfd93d6bae8aebbd109a83eaa611e27aa073053d02b90d1a0e3d3a86c61a"],"state_sha256":"e2ec9ef1308cff5824b4c040f7a248f291ac6416ba1457a36352c01464cdeac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+5upnnO+KPGXPixRJES73DTwlYQSNA8IGbGcCU/HrNpUemrcABAhiv8udkPZK48ybyRfAJQUwEm6oQ68dtUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:57:51.331609Z","bundle_sha256":"270e05270376ef0222f38a6e0128f27b11553db7622337e953b9223a2a783c23"}}