{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YO3LCODMCP67QHCQRVYXJY35YL","short_pith_number":"pith:YO3LCODM","schema_version":"1.0","canonical_sha256":"c3b6b1386c13fdf81c508d7174e37dc2e62eedc44ad248269a5bb03d95350455","source":{"kind":"arxiv","id":"2606.01820","version":1},"attestation_state":"computed","paper":{"title":"TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"2), (2) Karlsruhe University of Applied Sciences), Jannik Str\\\"otgen (2) ((1) Karlsruhe Institute of Technology, Oliver Hennh\\\"ofer (2), Shamira Venturini (1, Steffen Kinkel (2)","submitted_at":"2026-06-01T07:34:24Z","abstract_excerpt":"Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts. Developed under conditions of extreme data scarcity using children's narrative data, the system shows the feasibility of linguistic analysis in low-resource settings. Our evaluation demonstrates that TalkTag produces encouragingly precise annotation while effectively identifying instances"},"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":"2606.01820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T07:34:24Z","cross_cats_sorted":[],"title_canon_sha256":"659935e6ee4359bec93729c7459fda941816cbf96d00dd15f032e9ab12ffaba5","abstract_canon_sha256":"c7dd5e7706a8b0117e34b077ebff53e73b362407d443e32ee5a09ba81698917f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:57.776941Z","signature_b64":"sllqn4aErhGtNImdV+chgJu1LmjYcBJ0dcv3bS7ZD7XCfFRRrPBBhf3JJ46SwEhfGP2dt+JUFa0WYIQswXKBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b6b1386c13fdf81c508d7174e37dc2e62eedc44ad248269a5bb03d95350455","last_reissued_at":"2026-06-02T02:04:57.776592Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:57.776592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"2), (2) Karlsruhe University of Applied Sciences), Jannik Str\\\"otgen (2) ((1) Karlsruhe Institute of Technology, Oliver Hennh\\\"ofer (2), Shamira Venturini (1, Steffen Kinkel (2)","submitted_at":"2026-06-01T07:34:24Z","abstract_excerpt":"Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts. Developed under conditions of extreme data scarcity using children's narrative data, the system shows the feasibility of linguistic analysis in low-resource settings. Our evaluation demonstrates that TalkTag produces encouragingly precise annotation while effectively identifying instances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01820","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01820/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":"2606.01820","created_at":"2026-06-02T02:04:57.776648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01820v1","created_at":"2026-06-02T02:04:57.776648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01820","created_at":"2026-06-02T02:04:57.776648+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO3LCODMCP67","created_at":"2026-06-02T02:04:57.776648+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO3LCODMCP67QHCQ","created_at":"2026-06-02T02:04:57.776648+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO3LCODM","created_at":"2026-06-02T02:04:57.776648+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/YO3LCODMCP67QHCQRVYXJY35YL","json":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL.json","graph_json":"https://pith.science/api/pith-number/YO3LCODMCP67QHCQRVYXJY35YL/graph.json","events_json":"https://pith.science/api/pith-number/YO3LCODMCP67QHCQRVYXJY35YL/events.json","paper":"https://pith.science/paper/YO3LCODM"},"agent_actions":{"view_html":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL","download_json":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL.json","view_paper":"https://pith.science/paper/YO3LCODM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01820&json=true","fetch_graph":"https://pith.science/api/pith-number/YO3LCODMCP67QHCQRVYXJY35YL/graph.json","fetch_events":"https://pith.science/api/pith-number/YO3LCODMCP67QHCQRVYXJY35YL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL/action/storage_attestation","attest_author":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL/action/author_attestation","sign_citation":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL/action/citation_signature","submit_replication":"https://pith.science/pith/YO3LCODMCP67QHCQRVYXJY35YL/action/replication_record"}},"created_at":"2026-06-02T02:04:57.776648+00:00","updated_at":"2026-06-02T02:04:57.776648+00:00"}