{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NIFUYZS34HSLN7R3PJTGDFGQTB","short_pith_number":"pith:NIFUYZS3","schema_version":"1.0","canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","source":{"kind":"arxiv","id":"2203.08299","version":4},"attestation_state":"computed","paper":{"title":"FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caitlyn Chen, Maximillian Chen, Xiao Yu, Zhou Yu","submitted_at":"2022-03-15T22:33:26Z","abstract_excerpt":"Syntax is a fundamental component of language, yet few metrics have been employed to capture syntactic similarity or coherence at the utterance- and document-level. The existing standard document-level syntactic similarity metric is computationally expensive and performs inconsistently when faced with syntactically dissimilar documents. To address these challenges, we present FastKASSIM, a metric for utterance- and document-level syntactic similarity which pairs and averages the most similar constituency parse trees between a pair of documents based on tree kernels. FastKASSIM is more robust t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.08299","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T22:33:26Z","cross_cats_sorted":[],"title_canon_sha256":"057921553d17cd555a44ae0f50cd49815a7f7b0866d5d2c596f4821edd93ca29","abstract_canon_sha256":"395d9627fa382051c1bb109d5915ff3db6a12384c72ccf4ba82056ee983c2fb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:15.954781Z","signature_b64":"hTPuOVBj0TfMe74qH000dNA3/vcsNS7A6fv2AFctY4sD+QxLvA/YoPmsvAcFQ3dIjLBh7nOr1RQjqg0Nwj7ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","last_reissued_at":"2026-07-05T05:36:15.954333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:15.954333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caitlyn Chen, Maximillian Chen, Xiao Yu, Zhou Yu","submitted_at":"2022-03-15T22:33:26Z","abstract_excerpt":"Syntax is a fundamental component of language, yet few metrics have been employed to capture syntactic similarity or coherence at the utterance- and document-level. The existing standard document-level syntactic similarity metric is computationally expensive and performs inconsistently when faced with syntactically dissimilar documents. To address these challenges, we present FastKASSIM, a metric for utterance- and document-level syntactic similarity which pairs and averages the most similar constituency parse trees between a pair of documents based on tree kernels. FastKASSIM is more robust t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08299","kind":"arxiv","version":4},"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/2203.08299/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.08299","created_at":"2026-07-05T05:36:15.954389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08299v4","created_at":"2026-07-05T05:36:15.954389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08299","created_at":"2026-07-05T05:36:15.954389+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIFUYZS34HSL","created_at":"2026-07-05T05:36:15.954389+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIFUYZS34HSLN7R3","created_at":"2026-07-05T05:36:15.954389+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIFUYZS3","created_at":"2026-07-05T05:36:15.954389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB","json":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB.json","graph_json":"https://pith.science/api/pith-number/NIFUYZS34HSLN7R3PJTGDFGQTB/graph.json","events_json":"https://pith.science/api/pith-number/NIFUYZS34HSLN7R3PJTGDFGQTB/events.json","paper":"https://pith.science/paper/NIFUYZS3"},"agent_actions":{"view_html":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB","download_json":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB.json","view_paper":"https://pith.science/paper/NIFUYZS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08299&json=true","fetch_graph":"https://pith.science/api/pith-number/NIFUYZS34HSLN7R3PJTGDFGQTB/graph.json","fetch_events":"https://pith.science/api/pith-number/NIFUYZS34HSLN7R3PJTGDFGQTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/action/storage_attestation","attest_author":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/action/author_attestation","sign_citation":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/action/citation_signature","submit_replication":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/action/replication_record"}},"created_at":"2026-07-05T05:36:15.954389+00:00","updated_at":"2026-07-05T05:36:15.954389+00:00"}