{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3WSKCWPCMRZXETTWIPUZ7E2Q6A","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":"b5328f758ddbaacbc5d35a66c12572e5d9a863123aea281560593c83177442b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:11Z","title_canon_sha256":"ee4136539178ef18daaba4819097ed00052d390125344843828355ed98965627"},"schema_version":"1.0","source":{"id":"2503.03703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03703","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03703v1","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03703","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"3WSKCWPCMRZX","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"3WSKCWPCMRZXETTW","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"3WSKCWPC","created_at":"2026-07-05T10:24:59Z"}],"graph_snapshots":[{"event_id":"sha256:7936e3d1535ad18c835a289d12557cb2e0f079ef0c47bec606b5052f58427f81","target":"graph","created_at":"2026-07-05T10:24:59Z","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/2503.03703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Researchers and practitioners in natural language processing and computational linguistics frequently observe and analyze the real language usage in large-scale corpora. For that purpose, they often employ off-the-shelf pattern-matching tools, such as grep, and keyword-in-context concordancers, which is widely used in corpus linguistics for gathering examples. Nonetheless, these existing techniques rely on surface-level string matching, and thus they suffer from the major limitation of not being able to handle orthographic variations and paraphrasing -- notable and common phenomena in any natu","authors_text":"Chihiro Taguchi, Go kamoda, Hiroyuki Deguchi, Kohei Suenaga, Masaki Waga, Sho Yokoi, Yusuke Matsushita","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:11Z","title":"SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03703","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":"sha256:3ce032a07b08cb514742401cc377a99aced257c6acdbefd88bd8365b77fc6c84","target":"record","created_at":"2026-07-05T10:24:59Z","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":"b5328f758ddbaacbc5d35a66c12572e5d9a863123aea281560593c83177442b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:11Z","title_canon_sha256":"ee4136539178ef18daaba4819097ed00052d390125344843828355ed98965627"},"schema_version":"1.0","source":{"id":"2503.03703","kind":"arxiv","version":1}},"canonical_sha256":"dda4a159e26473724e7643e99f9350f034e8646533388c87fc87e8fcb0c7f3d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dda4a159e26473724e7643e99f9350f034e8646533388c87fc87e8fcb0c7f3d1","first_computed_at":"2026-07-05T10:24:59.252235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:59.252235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k3LB3gBFK4Ocx2f7+wnBY798aN7FFYzpOHgMBrE5B7cpCzX2IhFNdEd+EjPze6PLfOXCpEmoIBTWPm16FEYECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:59.252849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ce032a07b08cb514742401cc377a99aced257c6acdbefd88bd8365b77fc6c84","sha256:7936e3d1535ad18c835a289d12557cb2e0f079ef0c47bec606b5052f58427f81"],"state_sha256":"43efd9907b901756c07800ee037ad22703f46bba8e051eea5725c75791789490"}