{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A32UNU574P2CJ3ATALKTCXPWFA","short_pith_number":"pith:A32UNU57","schema_version":"1.0","canonical_sha256":"06f546d3bfe3f424ec1302d5315df6281a7dc4bf2af9ddec0065df4d0d83390c","source":{"kind":"arxiv","id":"2107.04736","version":1},"attestation_state":"computed","paper":{"title":"Assessing Data Efficiency in Task-Oriented Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Aly, Akshat Shrivastava, Alexander Zotov, Brian Moran, Justin Rill, Safiyyah Saleem, Shrey Desai","submitted_at":"2021-07-10T02:43:16Z","abstract_excerpt":"Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have, historically, varied widely across experiments. In our work, as a step towards providing a unified solution to data-efficiency-related questions, we introduce a four-stage protocol which gives an approximate measure of how much in-domain, \"target\" data a parser requires to achieve a certain quality bar. Specifically, our protocol consists of (1) sampling target subs"},"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":"2107.04736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-10T02:43:16Z","cross_cats_sorted":[],"title_canon_sha256":"24f152cb63dbe6aea40ac742bbde524313e33fd5d25ff516187cc547566dc361","abstract_canon_sha256":"29f6c426063409c2b8a5f40ed9af3776a4e0c8d9a3a79c821a256a62cebfcc1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:42.371972Z","signature_b64":"8isMhGfONI/ayhPx+hoOoMlSClfZeVPevyv4B2ge+LGdA2it21P2ROBEqEBGNM97Lz3WUqnQ2zhEKGz25uyxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06f546d3bfe3f424ec1302d5315df6281a7dc4bf2af9ddec0065df4d0d83390c","last_reissued_at":"2026-07-05T02:56:42.371580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:42.371580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing Data Efficiency in Task-Oriented Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Aly, Akshat Shrivastava, Alexander Zotov, Brian Moran, Justin Rill, Safiyyah Saleem, Shrey Desai","submitted_at":"2021-07-10T02:43:16Z","abstract_excerpt":"Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have, historically, varied widely across experiments. In our work, as a step towards providing a unified solution to data-efficiency-related questions, we introduce a four-stage protocol which gives an approximate measure of how much in-domain, \"target\" data a parser requires to achieve a certain quality bar. Specifically, our protocol consists of (1) sampling target subs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04736","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/2107.04736/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":"2107.04736","created_at":"2026-07-05T02:56:42.371636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04736v1","created_at":"2026-07-05T02:56:42.371636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04736","created_at":"2026-07-05T02:56:42.371636+00:00"},{"alias_kind":"pith_short_12","alias_value":"A32UNU574P2C","created_at":"2026-07-05T02:56:42.371636+00:00"},{"alias_kind":"pith_short_16","alias_value":"A32UNU574P2CJ3AT","created_at":"2026-07-05T02:56:42.371636+00:00"},{"alias_kind":"pith_short_8","alias_value":"A32UNU57","created_at":"2026-07-05T02:56:42.371636+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/A32UNU574P2CJ3ATALKTCXPWFA","json":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA.json","graph_json":"https://pith.science/api/pith-number/A32UNU574P2CJ3ATALKTCXPWFA/graph.json","events_json":"https://pith.science/api/pith-number/A32UNU574P2CJ3ATALKTCXPWFA/events.json","paper":"https://pith.science/paper/A32UNU57"},"agent_actions":{"view_html":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA","download_json":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA.json","view_paper":"https://pith.science/paper/A32UNU57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04736&json=true","fetch_graph":"https://pith.science/api/pith-number/A32UNU574P2CJ3ATALKTCXPWFA/graph.json","fetch_events":"https://pith.science/api/pith-number/A32UNU574P2CJ3ATALKTCXPWFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA/action/storage_attestation","attest_author":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA/action/author_attestation","sign_citation":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA/action/citation_signature","submit_replication":"https://pith.science/pith/A32UNU574P2CJ3ATALKTCXPWFA/action/replication_record"}},"created_at":"2026-07-05T02:56:42.371636+00:00","updated_at":"2026-07-05T02:56:42.371636+00:00"}