{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IAVOXLXYFGFER3LKRJHXTA6LLK","short_pith_number":"pith:IAVOXLXY","canonical_record":{"source":{"id":"1702.02640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T22:24:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09ee81a616863d4c55cbeb7c78ae9d606efe82296b9ebfca32151ca7b9da2643","abstract_canon_sha256":"8e7e4b6c8f8b555e06ab8769c44ad551d6dcc119184482c62adadd70d0e07781"},"schema_version":"1.0"},"canonical_sha256":"402aebaef8298a48ed6a8a4f7983cb5a88a29c161cfe8817ba1a8b450844869e","source":{"kind":"arxiv","id":"1702.02640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02640","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02640v1","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02640","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"IAVOXLXYFGFE","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IAVOXLXYFGFER3LK","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IAVOXLXY","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IAVOXLXYFGFER3LKRJHXTA6LLK","target":"record","payload":{"canonical_record":{"source":{"id":"1702.02640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T22:24:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09ee81a616863d4c55cbeb7c78ae9d606efe82296b9ebfca32151ca7b9da2643","abstract_canon_sha256":"8e7e4b6c8f8b555e06ab8769c44ad551d6dcc119184482c62adadd70d0e07781"},"schema_version":"1.0"},"canonical_sha256":"402aebaef8298a48ed6a8a4f7983cb5a88a29c161cfe8817ba1a8b450844869e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:03.814298Z","signature_b64":"JZNtIS7rf9jtslGxCY+u4ik10rjYNh3q265P3o49XEtRSRKJoNPzhyb8ENOt34YV7uRt9Gvka9BEtui4OmqGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402aebaef8298a48ed6a8a4f7983cb5a88a29c161cfe8817ba1a8b450844869e","last_reissued_at":"2026-05-18T00:51:03.813881Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:03.813881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.02640","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":"2026-05-18T00:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAsZkq9bC39hh3CjGy9yPCEJ8zBpc/OybJlcdXI4B/IG1g85UuAsNJOTEoX1XckuRZV3g1hcT6IyQGVlWWT9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:57:15.548332Z"},"content_sha256":"035d51fb2680bdd6cb2f7ba0f4dec34bf4a0f52031c7a82bba2f24929190d9a0","schema_version":"1.0","event_id":"sha256:035d51fb2680bdd6cb2f7ba0f4dec34bf4a0f52031c7a82bba2f24929190d9a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IAVOXLXYFGFER3LKRJHXTA6LLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Character-level Deep Conflation for Business Data Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameet Joshi, Jianfeng Gao, Jianshu Chen, Li Deng, P. D. Singh, Xiaodong He, Zhe Gan","submitted_at":"2017-02-08T22:24:14Z","abstract_excerpt":"Connecting different text attributes associated with the same entity (conflation) is important in business data analytics since it could help merge two different tables in a database to provide a more comprehensive profile of an entity. However, the conflation task is challenging because two text strings that describe the same entity could be quite different from each other for reasons such as misspelling. It is therefore critical to develop a conflation model that is able to truly understand the semantic meaning of the strings and match them at the semantic level. To this end, we develop a ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02640","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":"2026-05-18T00:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/5Ir3nWsVrJLXnJbgWbw8ZTpmzt5m2fXXReV3zp/PEDd0fafW+T7Ai8vUIFEnNkGER5PHMD0pz0PNKF9mVQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:57:15.548723Z"},"content_sha256":"c075559db86123a28cec179002c3a4f14f6a77b92970f04fa2ef33069670fa94","schema_version":"1.0","event_id":"sha256:c075559db86123a28cec179002c3a4f14f6a77b92970f04fa2ef33069670fa94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/bundle.json","state_url":"https://pith.science/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/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":"2026-05-31T08:57:15Z","links":{"resolver":"https://pith.science/pith/IAVOXLXYFGFER3LKRJHXTA6LLK","bundle":"https://pith.science/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/bundle.json","state":"https://pith.science/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAVOXLXYFGFER3LKRJHXTA6LLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IAVOXLXYFGFER3LKRJHXTA6LLK","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":"8e7e4b6c8f8b555e06ab8769c44ad551d6dcc119184482c62adadd70d0e07781","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T22:24:14Z","title_canon_sha256":"09ee81a616863d4c55cbeb7c78ae9d606efe82296b9ebfca32151ca7b9da2643"},"schema_version":"1.0","source":{"id":"1702.02640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02640","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02640v1","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02640","created_at":"2026-05-18T00:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"IAVOXLXYFGFE","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IAVOXLXYFGFER3LK","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IAVOXLXY","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:c075559db86123a28cec179002c3a4f14f6a77b92970f04fa2ef33069670fa94","target":"graph","created_at":"2026-05-18T00:51:03Z","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":"Connecting different text attributes associated with the same entity (conflation) is important in business data analytics since it could help merge two different tables in a database to provide a more comprehensive profile of an entity. However, the conflation task is challenging because two text strings that describe the same entity could be quite different from each other for reasons such as misspelling. It is therefore critical to develop a conflation model that is able to truly understand the semantic meaning of the strings and match them at the semantic level. To this end, we develop a ch","authors_text":"Ameet Joshi, Jianfeng Gao, Jianshu Chen, Li Deng, P. D. Singh, Xiaodong He, Zhe Gan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T22:24:14Z","title":"Character-level Deep Conflation for Business Data Analytics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02640","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":"sha256:035d51fb2680bdd6cb2f7ba0f4dec34bf4a0f52031c7a82bba2f24929190d9a0","target":"record","created_at":"2026-05-18T00:51:03Z","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":"8e7e4b6c8f8b555e06ab8769c44ad551d6dcc119184482c62adadd70d0e07781","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T22:24:14Z","title_canon_sha256":"09ee81a616863d4c55cbeb7c78ae9d606efe82296b9ebfca32151ca7b9da2643"},"schema_version":"1.0","source":{"id":"1702.02640","kind":"arxiv","version":1}},"canonical_sha256":"402aebaef8298a48ed6a8a4f7983cb5a88a29c161cfe8817ba1a8b450844869e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"402aebaef8298a48ed6a8a4f7983cb5a88a29c161cfe8817ba1a8b450844869e","first_computed_at":"2026-05-18T00:51:03.813881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:03.813881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZNtIS7rf9jtslGxCY+u4ik10rjYNh3q265P3o49XEtRSRKJoNPzhyb8ENOt34YV7uRt9Gvka9BEtui4OmqGCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:03.814298Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.02640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:035d51fb2680bdd6cb2f7ba0f4dec34bf4a0f52031c7a82bba2f24929190d9a0","sha256:c075559db86123a28cec179002c3a4f14f6a77b92970f04fa2ef33069670fa94"],"state_sha256":"e2f34aed4bdd57584c5a2bc3d450d9ba6d0fb820e3f6b89055260d59804c53f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORzRwI0IzIzn1Udm0PM9vFjRA2FNPQ0FE1TG1ZLeTES8D7ycXBjZiD2J4xv6Xq9WvkJPlXTRRjNKNkDRez8oCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T08:57:15.551325Z","bundle_sha256":"aa47db2b7d4e74c3b1cfe31dd69b7df13a49c657f3bcba71af7e96a160bd16dd"}}