{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XZHKI3FV2P4PORD33UPR36WRSU","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":"3fc2d1ff3015884c3779f8f447d92afbdfb82bb086d1f00886f219a0958f1028","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-29T02:53:59Z","title_canon_sha256":"e94269043f3118c1892d5c78b10ecc5664089e5b3837757823e8f936158c3aca"},"schema_version":"1.0","source":{"id":"2106.15065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15065","created_at":"2026-07-05T02:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15065v1","created_at":"2026-07-05T02:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15065","created_at":"2026-07-05T02:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"XZHKI3FV2P4P","created_at":"2026-07-05T02:53:04Z"},{"alias_kind":"pith_short_16","alias_value":"XZHKI3FV2P4PORD3","created_at":"2026-07-05T02:53:04Z"},{"alias_kind":"pith_short_8","alias_value":"XZHKI3FV","created_at":"2026-07-05T02:53:04Z"}],"graph_snapshots":[{"event_id":"sha256:3de412172623ec099cc191c499192f92e588a0a1b818652ce6d8925eb8fa4f2b","target":"graph","created_at":"2026-07-05T02:53:04Z","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/2106.15065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decomposable tasks are complex and comprise of a hierarchy of sub-tasks. Spoken intent prediction, for example, combines automatic speech recognition and natural language understanding. Existing benchmarks, however, typically hold out examples for only the surface-level sub-task. As a result, models with similar performance on these benchmarks may have unobserved performance differences on the other sub-tasks. To allow insightful comparisons between competitive end-to-end architectures, we propose a framework to construct robust test sets using coordinate ascent over sub-task specific utility ","authors_text":"Alan W Black, Alissa Ostapenko, Florian Metze, Shinji Watanabe, Siddhant Arora, Siddharth Dalmia, Vijay Viswanathan","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-29T02:53:59Z","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15065","kind":"arxiv","version":1},"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":"sha256:216acd2d1cdbb4c5b1edd0739968987f33c811024ffe058439981f1b8c99efd4","target":"record","created_at":"2026-07-05T02:53:04Z","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":"3fc2d1ff3015884c3779f8f447d92afbdfb82bb086d1f00886f219a0958f1028","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-29T02:53:59Z","title_canon_sha256":"e94269043f3118c1892d5c78b10ecc5664089e5b3837757823e8f936158c3aca"},"schema_version":"1.0","source":{"id":"2106.15065","kind":"arxiv","version":1}},"canonical_sha256":"be4ea46cb5d3f8f7447bdd1f1dfad1951e512ac572a3c28a2c1782a0f102c67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be4ea46cb5d3f8f7447bdd1f1dfad1951e512ac572a3c28a2c1782a0f102c67a","first_computed_at":"2026-07-05T02:53:04.907269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:53:04.907269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l7E3MQ3ZWihDiPalfXg8XoshgsQLxOMkh/1yHx+k7FTTug7Is9w1wpeAf47Yv95kH0DpnnQEXYBzW+3lXhjYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:53:04.907752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:216acd2d1cdbb4c5b1edd0739968987f33c811024ffe058439981f1b8c99efd4","sha256:3de412172623ec099cc191c499192f92e588a0a1b818652ce6d8925eb8fa4f2b"],"state_sha256":"8f1ecc22feb5b0b61c1b3b10a4743619f1d5fb15a200e5f1b47a0528efde82ea"}