{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NIFUYZS34HSLN7R3PJTGDFGQTB","short_pith_number":"pith:NIFUYZS3","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"},"canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","source":{"kind":"arxiv","id":"2203.08299","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08299","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08299v4","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08299","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"NIFUYZS34HSL","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_16","alias_value":"NIFUYZS34HSLN7R3","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_8","alias_value":"NIFUYZS3","created_at":"2026-07-05T05:36:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NIFUYZS34HSLN7R3PJTGDFGQTB","target":"record","payload":{"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"},"canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","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"},"source_kind":"arxiv","source_id":"2203.08299","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLOi4pSbBmlOGt8jXB1Mz3zOAdgkBR5vnm7XTUpB48HjDeDqumUBlSuwi2MLudOdMbjqNzSiPWo9kg24R5o7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:43:23.205044Z"},"content_sha256":"0eccf5b23b0391399d74348113ae25369084f7dc58bbbb77af359c4e3951d81a","schema_version":"1.0","event_id":"sha256:0eccf5b23b0391399d74348113ae25369084f7dc58bbbb77af359c4e3951d81a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NIFUYZS34HSLN7R3PJTGDFGQTB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7/0tpFwWTMCk6qZcZ4R2GYv+cAwek2hdgQ2GdGgyIiYjyVQwcey4ns8C4n6bEYkWWMsj+s5pGeWe6Fss6bJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:43:23.205421Z"},"content_sha256":"a396535a81f84f9774e886c61cbf72b2b5cbbe9d724621678c3a4b2a73596e4d","schema_version":"1.0","event_id":"sha256:a396535a81f84f9774e886c61cbf72b2b5cbbe9d724621678c3a4b2a73596e4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/bundle.json","state_url":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/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":"2026-07-24T11:43:23Z","links":{"resolver":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB","bundle":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/bundle.json","state":"https://pith.science/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIFUYZS34HSLN7R3PJTGDFGQTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NIFUYZS34HSLN7R3PJTGDFGQTB","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":"395d9627fa382051c1bb109d5915ff3db6a12384c72ccf4ba82056ee983c2fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T22:33:26Z","title_canon_sha256":"057921553d17cd555a44ae0f50cd49815a7f7b0866d5d2c596f4821edd93ca29"},"schema_version":"1.0","source":{"id":"2203.08299","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08299","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08299v4","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08299","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"NIFUYZS34HSL","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_16","alias_value":"NIFUYZS34HSLN7R3","created_at":"2026-07-05T05:36:15Z"},{"alias_kind":"pith_short_8","alias_value":"NIFUYZS3","created_at":"2026-07-05T05:36:15Z"}],"graph_snapshots":[{"event_id":"sha256:a396535a81f84f9774e886c61cbf72b2b5cbbe9d724621678c3a4b2a73596e4d","target":"graph","created_at":"2026-07-05T05:36:15Z","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/2203.08299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caitlyn Chen, Maximillian Chen, Xiao Yu, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T22:33:26Z","title":"FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08299","kind":"arxiv","version":4},"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":"sha256:0eccf5b23b0391399d74348113ae25369084f7dc58bbbb77af359c4e3951d81a","target":"record","created_at":"2026-07-05T05:36:15Z","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":"395d9627fa382051c1bb109d5915ff3db6a12384c72ccf4ba82056ee983c2fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T22:33:26Z","title_canon_sha256":"057921553d17cd555a44ae0f50cd49815a7f7b0866d5d2c596f4821edd93ca29"},"schema_version":"1.0","source":{"id":"2203.08299","kind":"arxiv","version":4}},"canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a0b4c665be1e4b6fe3b7a666194d0984c07a52847dd429372339a4ba837a01f","first_computed_at":"2026-07-05T05:36:15.954333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:15.954333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hTPuOVBj0TfMe74qH000dNA3/vcsNS7A6fv2AFctY4sD+QxLvA/YoPmsvAcFQ3dIjLBh7nOr1RQjqg0Nwj7ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:15.954781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08299","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eccf5b23b0391399d74348113ae25369084f7dc58bbbb77af359c4e3951d81a","sha256:a396535a81f84f9774e886c61cbf72b2b5cbbe9d724621678c3a4b2a73596e4d"],"state_sha256":"e03143d236bdea4be4f835457b3948eea7927078be5867ff0792796af04a1f59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k3cmK5Ymz9+Cu6rQMceBg/U/RsmH6JzBLjYlieNJBnXX2zPf0UU5hTQ4YPRoiaItPxCX/l2Qhe0BTLp0FG5QBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T11:43:23.207473Z","bundle_sha256":"488edfe118702ee229f18288a374f8d064fcafa3ab30f8bfbde24f97af7a89b8"}}