{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NEP22TYRZRD4PG7B3QAUUBRAPQ","short_pith_number":"pith:NEP22TYR","schema_version":"1.0","canonical_sha256":"691fad4f11cc47c79be1dc014a06207c068d5a5b6a500e10749adb132aeb83af","source":{"kind":"arxiv","id":"2204.05483","version":2},"attestation_state":"computed","paper":{"title":"Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Leach, Stefan Larson","submitted_at":"2022-04-12T02:28:23Z","abstract_excerpt":"Dialog systems must be capable of incorporating new skills via updates over time in order to reflect new use cases or deployment scenarios. Similarly, developers of such ML-driven systems need to be able to add new training data to an already-existing dataset to support these new skills. In intent classification systems, problems can arise if training data for a new skill's intent overlaps semantically with an already-existing intent. We call such cases collisions. This paper introduces the task of intent collision detection between multiple datasets for the purposes of growing a system's skil"},"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":"2204.05483","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T02:28:23Z","cross_cats_sorted":[],"title_canon_sha256":"1b7b388ff264e59e87e066f84127c14ecc2dadd5080021dd6b31150592d9e04b","abstract_canon_sha256":"e3381932f7b10de04c2d285b7ec7a5ece547f344e7209d2d1b1f587370a70599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:00.997707Z","signature_b64":"XN+DIlasHtwPrXSK06ExEStlsGGUSDfcHQIDpj2YdSQPC2WdqMbc/YXQ8iMMR1ahwPOKH9yGCo4z5qUyTXCPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"691fad4f11cc47c79be1dc014a06207c068d5a5b6a500e10749adb132aeb83af","last_reissued_at":"2026-07-05T04:43:00.997206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:00.997206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Leach, Stefan Larson","submitted_at":"2022-04-12T02:28:23Z","abstract_excerpt":"Dialog systems must be capable of incorporating new skills via updates over time in order to reflect new use cases or deployment scenarios. Similarly, developers of such ML-driven systems need to be able to add new training data to an already-existing dataset to support these new skills. In intent classification systems, problems can arise if training data for a new skill's intent overlaps semantically with an already-existing intent. We call such cases collisions. This paper introduces the task of intent collision detection between multiple datasets for the purposes of growing a system's skil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05483","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/2204.05483/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":"2204.05483","created_at":"2026-07-05T04:43:00.997256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05483v2","created_at":"2026-07-05T04:43:00.997256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05483","created_at":"2026-07-05T04:43:00.997256+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEP22TYRZRD4","created_at":"2026-07-05T04:43:00.997256+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEP22TYRZRD4PG7B","created_at":"2026-07-05T04:43:00.997256+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEP22TYR","created_at":"2026-07-05T04:43:00.997256+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/NEP22TYRZRD4PG7B3QAUUBRAPQ","json":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ.json","graph_json":"https://pith.science/api/pith-number/NEP22TYRZRD4PG7B3QAUUBRAPQ/graph.json","events_json":"https://pith.science/api/pith-number/NEP22TYRZRD4PG7B3QAUUBRAPQ/events.json","paper":"https://pith.science/paper/NEP22TYR"},"agent_actions":{"view_html":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ","download_json":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ.json","view_paper":"https://pith.science/paper/NEP22TYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05483&json=true","fetch_graph":"https://pith.science/api/pith-number/NEP22TYRZRD4PG7B3QAUUBRAPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NEP22TYRZRD4PG7B3QAUUBRAPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ/action/storage_attestation","attest_author":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ/action/author_attestation","sign_citation":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ/action/citation_signature","submit_replication":"https://pith.science/pith/NEP22TYRZRD4PG7B3QAUUBRAPQ/action/replication_record"}},"created_at":"2026-07-05T04:43:00.997256+00:00","updated_at":"2026-07-05T04:43:00.997256+00:00"}