{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NEP22TYRZRD4PG7B3QAUUBRAPQ","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":"e3381932f7b10de04c2d285b7ec7a5ece547f344e7209d2d1b1f587370a70599","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T02:28:23Z","title_canon_sha256":"1b7b388ff264e59e87e066f84127c14ecc2dadd5080021dd6b31150592d9e04b"},"schema_version":"1.0","source":{"id":"2204.05483","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05483","created_at":"2026-07-05T04:43:00Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05483v2","created_at":"2026-07-05T04:43:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05483","created_at":"2026-07-05T04:43:00Z"},{"alias_kind":"pith_short_12","alias_value":"NEP22TYRZRD4","created_at":"2026-07-05T04:43:00Z"},{"alias_kind":"pith_short_16","alias_value":"NEP22TYRZRD4PG7B","created_at":"2026-07-05T04:43:00Z"},{"alias_kind":"pith_short_8","alias_value":"NEP22TYR","created_at":"2026-07-05T04:43:00Z"}],"graph_snapshots":[{"event_id":"sha256:ebb976bd72d4f832e375d35f05d030fa1853534c06ace28d6f4483fb60439950","target":"graph","created_at":"2026-07-05T04:43:00Z","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/2204.05483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kevin Leach, Stefan Larson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T02:28:23Z","title":"Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05483","kind":"arxiv","version":2},"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:d316167993c8df246c2d1db0f8d7820a38bf9dd8b38a9b007093258e399a8e72","target":"record","created_at":"2026-07-05T04:43:00Z","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":"e3381932f7b10de04c2d285b7ec7a5ece547f344e7209d2d1b1f587370a70599","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T02:28:23Z","title_canon_sha256":"1b7b388ff264e59e87e066f84127c14ecc2dadd5080021dd6b31150592d9e04b"},"schema_version":"1.0","source":{"id":"2204.05483","kind":"arxiv","version":2}},"canonical_sha256":"691fad4f11cc47c79be1dc014a06207c068d5a5b6a500e10749adb132aeb83af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"691fad4f11cc47c79be1dc014a06207c068d5a5b6a500e10749adb132aeb83af","first_computed_at":"2026-07-05T04:43:00.997206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:00.997206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XN+DIlasHtwPrXSK06ExEStlsGGUSDfcHQIDpj2YdSQPC2WdqMbc/YXQ8iMMR1ahwPOKH9yGCo4z5qUyTXCPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:00.997707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05483","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d316167993c8df246c2d1db0f8d7820a38bf9dd8b38a9b007093258e399a8e72","sha256:ebb976bd72d4f832e375d35f05d030fa1853534c06ace28d6f4483fb60439950"],"state_sha256":"5c82dc4727fbfbb76b50a4a3064322475433ac43f9ec890ff35e3a63f4e52e05"}