{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZPV52MPW5W6C74H6LXM23TVP3Z","short_pith_number":"pith:ZPV52MPW","schema_version":"1.0","canonical_sha256":"cbebdd31f6edbc2ff0fe5dd9adceafde42cc7f807366bb3d1ebf64c25cee4cd9","source":{"kind":"arxiv","id":"2311.08481","version":2},"attestation_state":"computed","paper":{"title":"Functionality learning through specification instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Roth, Pedro Henrique Luz de Araujo","submitted_at":"2023-11-14T19:15:55Z","abstract_excerpt":"Test suites assess natural language processing models' performance on specific functionalities: cases of interest involving model robustness, fairness, or particular linguistic capabilities. This paper introduces specification instructions: text descriptions specifying fine-grained task-specific behaviors. For each functionality in a suite, we generate an instruction that describes it. We combine the specification instructions to create specification-augmented prompts, which we feed to language models pre-trained on natural instruction data.\n  We conduct experiments to measure how optimizing f"},"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":"2311.08481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T19:15:55Z","cross_cats_sorted":[],"title_canon_sha256":"d1de2d666825fe921856c3a83d0c76e5ecea12c76deee0911668e08869655cf2","abstract_canon_sha256":"947e90db6304f01282b012c4b1ee0ab4dc274e5bb898ff2ceaf8da972f264efb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:37.301128Z","signature_b64":"c1LLsc5BFMp5um8h3+OXBrwbd1VS3E3WLoq4FRGXihDral0oA5ATLJ+DB/Cnu8El+VrWKaTdRekozWqC/KJSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbebdd31f6edbc2ff0fe5dd9adceafde42cc7f807366bb3d1ebf64c25cee4cd9","last_reissued_at":"2026-07-05T09:36:37.300709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:37.300709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Functionality learning through specification instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Roth, Pedro Henrique Luz de Araujo","submitted_at":"2023-11-14T19:15:55Z","abstract_excerpt":"Test suites assess natural language processing models' performance on specific functionalities: cases of interest involving model robustness, fairness, or particular linguistic capabilities. This paper introduces specification instructions: text descriptions specifying fine-grained task-specific behaviors. For each functionality in a suite, we generate an instruction that describes it. We combine the specification instructions to create specification-augmented prompts, which we feed to language models pre-trained on natural instruction data.\n  We conduct experiments to measure how optimizing f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08481","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/2311.08481/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":"2311.08481","created_at":"2026-07-05T09:36:37.300762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08481v2","created_at":"2026-07-05T09:36:37.300762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08481","created_at":"2026-07-05T09:36:37.300762+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPV52MPW5W6C","created_at":"2026-07-05T09:36:37.300762+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPV52MPW5W6C74H6","created_at":"2026-07-05T09:36:37.300762+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPV52MPW","created_at":"2026-07-05T09:36:37.300762+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/ZPV52MPW5W6C74H6LXM23TVP3Z","json":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z.json","graph_json":"https://pith.science/api/pith-number/ZPV52MPW5W6C74H6LXM23TVP3Z/graph.json","events_json":"https://pith.science/api/pith-number/ZPV52MPW5W6C74H6LXM23TVP3Z/events.json","paper":"https://pith.science/paper/ZPV52MPW"},"agent_actions":{"view_html":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z","download_json":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z.json","view_paper":"https://pith.science/paper/ZPV52MPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08481&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPV52MPW5W6C74H6LXM23TVP3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPV52MPW5W6C74H6LXM23TVP3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z/action/storage_attestation","attest_author":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z/action/author_attestation","sign_citation":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z/action/citation_signature","submit_replication":"https://pith.science/pith/ZPV52MPW5W6C74H6LXM23TVP3Z/action/replication_record"}},"created_at":"2026-07-05T09:36:37.300762+00:00","updated_at":"2026-07-05T09:36:37.300762+00:00"}