{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7LX4QRRVEFRKEHM5QT54MW3KJM","short_pith_number":"pith:7LX4QRRV","schema_version":"1.0","canonical_sha256":"faefc846352162a21d9d84fbc65b6a4b1c97cbac52e8319a733f0131e5911f96","source":{"kind":"arxiv","id":"2507.05010","version":1},"attestation_state":"computed","paper":{"title":"Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Chenfei Xiong, Dirk Hovy, Donya Rooein, Elliott Ash, Jingwei Ni, Lorena Calvo-Bartolom\\'e, Markus Leippold, Mennatallah El-Assady, Mrinmaya Sachan, Vil\\'em Zouhar, Yu Fan, Zhijing Jin","submitted_at":"2025-07-07T13:48:54Z","abstract_excerpt":"We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETECT starts with an initial, sketch-level codebook and dataset provided by a domain expert, then leverages the LLM to annotate the data and identify edge cases that are not well described by the initial codebook. Specifically, Co-DETECT flags challenging examples, induces high-level, generalizable descriptions of edge cases, and assists user in incorporating edg"},"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":"2507.05010","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T13:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"a336b939712792e306ba080cb1b3478a3011652fedf255136a0ae8db950e9544","abstract_canon_sha256":"d5af39ef8857d75767190a075ebc61971ee74642bbcb2c0e8d15eeddc7e3e58f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:07.894752Z","signature_b64":"eFTz6XDmC2fZCtLkh/S8Ru2mAfP+/yX7ibc/WjQWzB2e0ZdLxi+/eIA2Gzg2U5WHlRAW1wIm6q99Dg0SYmJ2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faefc846352162a21d9d84fbc65b6a4b1c97cbac52e8319a733f0131e5911f96","last_reissued_at":"2026-07-05T11:33:07.894246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:07.894246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Chenfei Xiong, Dirk Hovy, Donya Rooein, Elliott Ash, Jingwei Ni, Lorena Calvo-Bartolom\\'e, Markus Leippold, Mennatallah El-Assady, Mrinmaya Sachan, Vil\\'em Zouhar, Yu Fan, Zhijing Jin","submitted_at":"2025-07-07T13:48:54Z","abstract_excerpt":"We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETECT starts with an initial, sketch-level codebook and dataset provided by a domain expert, then leverages the LLM to annotate the data and identify edge cases that are not well described by the initial codebook. Specifically, Co-DETECT flags challenging examples, induces high-level, generalizable descriptions of edge cases, and assists user in incorporating edg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05010","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/2507.05010/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":"2507.05010","created_at":"2026-07-05T11:33:07.894311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05010v1","created_at":"2026-07-05T11:33:07.894311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05010","created_at":"2026-07-05T11:33:07.894311+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LX4QRRVEFRK","created_at":"2026-07-05T11:33:07.894311+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LX4QRRVEFRKEHM5","created_at":"2026-07-05T11:33:07.894311+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LX4QRRV","created_at":"2026-07-05T11:33:07.894311+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/7LX4QRRVEFRKEHM5QT54MW3KJM","json":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM.json","graph_json":"https://pith.science/api/pith-number/7LX4QRRVEFRKEHM5QT54MW3KJM/graph.json","events_json":"https://pith.science/api/pith-number/7LX4QRRVEFRKEHM5QT54MW3KJM/events.json","paper":"https://pith.science/paper/7LX4QRRV"},"agent_actions":{"view_html":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM","download_json":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM.json","view_paper":"https://pith.science/paper/7LX4QRRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05010&json=true","fetch_graph":"https://pith.science/api/pith-number/7LX4QRRVEFRKEHM5QT54MW3KJM/graph.json","fetch_events":"https://pith.science/api/pith-number/7LX4QRRVEFRKEHM5QT54MW3KJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM/action/storage_attestation","attest_author":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM/action/author_attestation","sign_citation":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM/action/citation_signature","submit_replication":"https://pith.science/pith/7LX4QRRVEFRKEHM5QT54MW3KJM/action/replication_record"}},"created_at":"2026-07-05T11:33:07.894311+00:00","updated_at":"2026-07-05T11:33:07.894311+00:00"}