{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FK24VCWTQDX6BCKJLQX3KHFKK7","short_pith_number":"pith:FK24VCWT","schema_version":"1.0","canonical_sha256":"2ab5ca8ad380efe089495c2fb51caa57f8f3387442eaf191dd71c1485c6882bc","source":{"kind":"arxiv","id":"2602.06307","version":2},"attestation_state":"computed","paper":{"title":"Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Holly Hendrix, Justin Mackie, Megan Michelle Smith, Nelvin Licona-Guevara, Nemika Tyagi, Olga Kellert, Phanos Kareen, Samhitha Harish, Tatiana Gallego Hernande","submitted_at":"2026-02-06T02:02:07Z","abstract_excerpt":"Spoken bilingual conversations pose substantial challenges for syntactic parsing because they often include disfluencies and discourse-driven structures that complicate dependency parsing under standard Universal Dependencies (UD) assumptions and evaluation practices. To systematically study these challenges, in this work, we first introduce a linguistically grounded taxonomy of conversational bilingual phenomena, together with SpokeBench, an expert-annotated English-Spanish benchmark for structurally complex speech. To address the limitations of existing evaluation practices, we propose Flex-"},"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":"2602.06307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-06T02:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"bc2084ee69a0e95f7769d45486f37873d39bb1351ef60c099e05e4e190d1e851","abstract_canon_sha256":"ec34a5f03e1347f8396538dd1e7f7e91bb715ef2d04eb5053a48ee5e88a44b1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:19.688229Z","signature_b64":"zLy+EkAOMHoJMIsCwVoCHDttrjh3j7ArXZTdrsTM3GiP9FStMlw7A8UFSoZN00ywA8jzQD0OJWqL6p38/ogdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ab5ca8ad380efe089495c2fb51caa57f8f3387442eaf191dd71c1485c6882bc","last_reissued_at":"2026-06-09T02:07:19.687278Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:19.687278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Holly Hendrix, Justin Mackie, Megan Michelle Smith, Nelvin Licona-Guevara, Nemika Tyagi, Olga Kellert, Phanos Kareen, Samhitha Harish, Tatiana Gallego Hernande","submitted_at":"2026-02-06T02:02:07Z","abstract_excerpt":"Spoken bilingual conversations pose substantial challenges for syntactic parsing because they often include disfluencies and discourse-driven structures that complicate dependency parsing under standard Universal Dependencies (UD) assumptions and evaluation practices. To systematically study these challenges, in this work, we first introduce a linguistically grounded taxonomy of conversational bilingual phenomena, together with SpokeBench, an expert-annotated English-Spanish benchmark for structurally complex speech. To address the limitations of existing evaluation practices, we propose Flex-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06307","kind":"arxiv","version":2},"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/2602.06307/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":"2602.06307","created_at":"2026-06-09T02:07:19.687421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06307v2","created_at":"2026-06-09T02:07:19.687421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06307","created_at":"2026-06-09T02:07:19.687421+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK24VCWTQDX6","created_at":"2026-06-09T02:07:19.687421+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK24VCWTQDX6BCKJ","created_at":"2026-06-09T02:07:19.687421+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK24VCWT","created_at":"2026-06-09T02:07:19.687421+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/FK24VCWTQDX6BCKJLQX3KHFKK7","json":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7.json","graph_json":"https://pith.science/api/pith-number/FK24VCWTQDX6BCKJLQX3KHFKK7/graph.json","events_json":"https://pith.science/api/pith-number/FK24VCWTQDX6BCKJLQX3KHFKK7/events.json","paper":"https://pith.science/paper/FK24VCWT"},"agent_actions":{"view_html":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7","download_json":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7.json","view_paper":"https://pith.science/paper/FK24VCWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06307&json=true","fetch_graph":"https://pith.science/api/pith-number/FK24VCWTQDX6BCKJLQX3KHFKK7/graph.json","fetch_events":"https://pith.science/api/pith-number/FK24VCWTQDX6BCKJLQX3KHFKK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7/action/storage_attestation","attest_author":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7/action/author_attestation","sign_citation":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7/action/citation_signature","submit_replication":"https://pith.science/pith/FK24VCWTQDX6BCKJLQX3KHFKK7/action/replication_record"}},"created_at":"2026-06-09T02:07:19.687421+00:00","updated_at":"2026-06-09T02:07:19.687421+00:00"}