{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NW5HOPP6QEQRJL3AMJPJCPBRGE","short_pith_number":"pith:NW5HOPP6","schema_version":"1.0","canonical_sha256":"6dba773dfe812114af60625e913c31313bcdb81f229cdc2a4bc6085098da9de5","source":{"kind":"arxiv","id":"2212.00006","version":1},"attestation_state":"computed","paper":{"title":"Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.CY"],"primary_cat":"cs.HC","authors_text":"Arul Menezes, Matt Post, Vikas Raunak","submitted_at":"2022-11-19T06:39:43Z","abstract_excerpt":"In this work, we present some recommendations on the evaluation of state-of-the-art generative models for constrained generation tasks. The progress on generative models has been rapid in recent years. These large-scale models have had three impacts: firstly, the fluency of generation in both language and vision modalities has rendered common average-case evaluation metrics much less useful in diagnosing system errors. Secondly, the same substrate models now form the basis of a number of applications, driven both by the utility of their representations as well as phenomena such as in-context l"},"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":"2212.00006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-11-19T06:39:43Z","cross_cats_sorted":["cs.CL","cs.CV","cs.CY"],"title_canon_sha256":"f2ac2714cd467479563d0a40adde32aabe1290656cbc4019da0be7b0c0857fe5","abstract_canon_sha256":"e6657930a97f73411fccc73ef85380fcef74d0cfbfd5fd97e2829fe01350fb79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:16.822407Z","signature_b64":"BRhXJ+zX8Oaoij7vKNQXyPSJjqSsdBn7shbRS7cSTreGjzcg76KKM7dOk2eFtotpTbrAVdASe3GFfmRn5ZMqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dba773dfe812114af60625e913c31313bcdb81f229cdc2a4bc6085098da9de5","last_reissued_at":"2026-07-05T05:21:16.821926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:16.821926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.CY"],"primary_cat":"cs.HC","authors_text":"Arul Menezes, Matt Post, Vikas Raunak","submitted_at":"2022-11-19T06:39:43Z","abstract_excerpt":"In this work, we present some recommendations on the evaluation of state-of-the-art generative models for constrained generation tasks. The progress on generative models has been rapid in recent years. These large-scale models have had three impacts: firstly, the fluency of generation in both language and vision modalities has rendered common average-case evaluation metrics much less useful in diagnosing system errors. Secondly, the same substrate models now form the basis of a number of applications, driven both by the utility of their representations as well as phenomena such as in-context l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00006","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/2212.00006/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":"2212.00006","created_at":"2026-07-05T05:21:16.821999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00006v1","created_at":"2026-07-05T05:21:16.821999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00006","created_at":"2026-07-05T05:21:16.821999+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW5HOPP6QEQR","created_at":"2026-07-05T05:21:16.821999+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW5HOPP6QEQRJL3A","created_at":"2026-07-05T05:21:16.821999+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW5HOPP6","created_at":"2026-07-05T05:21:16.821999+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/NW5HOPP6QEQRJL3AMJPJCPBRGE","json":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE.json","graph_json":"https://pith.science/api/pith-number/NW5HOPP6QEQRJL3AMJPJCPBRGE/graph.json","events_json":"https://pith.science/api/pith-number/NW5HOPP6QEQRJL3AMJPJCPBRGE/events.json","paper":"https://pith.science/paper/NW5HOPP6"},"agent_actions":{"view_html":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE","download_json":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE.json","view_paper":"https://pith.science/paper/NW5HOPP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00006&json=true","fetch_graph":"https://pith.science/api/pith-number/NW5HOPP6QEQRJL3AMJPJCPBRGE/graph.json","fetch_events":"https://pith.science/api/pith-number/NW5HOPP6QEQRJL3AMJPJCPBRGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE/action/storage_attestation","attest_author":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE/action/author_attestation","sign_citation":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE/action/citation_signature","submit_replication":"https://pith.science/pith/NW5HOPP6QEQRJL3AMJPJCPBRGE/action/replication_record"}},"created_at":"2026-07-05T05:21:16.821999+00:00","updated_at":"2026-07-05T05:21:16.821999+00:00"}