{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NW5HOPP6QEQRJL3AMJPJCPBRGE","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":"e6657930a97f73411fccc73ef85380fcef74d0cfbfd5fd97e2829fe01350fb79","cross_cats_sorted":["cs.CL","cs.CV","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-11-19T06:39:43Z","title_canon_sha256":"f2ac2714cd467479563d0a40adde32aabe1290656cbc4019da0be7b0c0857fe5"},"schema_version":"1.0","source":{"id":"2212.00006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00006","created_at":"2026-07-05T05:21:16Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00006v1","created_at":"2026-07-05T05:21:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00006","created_at":"2026-07-05T05:21:16Z"},{"alias_kind":"pith_short_12","alias_value":"NW5HOPP6QEQR","created_at":"2026-07-05T05:21:16Z"},{"alias_kind":"pith_short_16","alias_value":"NW5HOPP6QEQRJL3A","created_at":"2026-07-05T05:21:16Z"},{"alias_kind":"pith_short_8","alias_value":"NW5HOPP6","created_at":"2026-07-05T05:21:16Z"}],"graph_snapshots":[{"event_id":"sha256:6ad316daa16891107d84a087ec1d969937eab155e5cd29a30710a0b23a5f97ec","target":"graph","created_at":"2026-07-05T05:21:16Z","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/2212.00006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arul Menezes, Matt Post, Vikas Raunak","cross_cats":["cs.CL","cs.CV","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-11-19T06:39:43Z","title":"Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00006","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:fb3fb3bd59750e85e048d1fe2f2b5e5c6c87ba507bfb47e8083b596850f5bca6","target":"record","created_at":"2026-07-05T05:21:16Z","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":"e6657930a97f73411fccc73ef85380fcef74d0cfbfd5fd97e2829fe01350fb79","cross_cats_sorted":["cs.CL","cs.CV","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-11-19T06:39:43Z","title_canon_sha256":"f2ac2714cd467479563d0a40adde32aabe1290656cbc4019da0be7b0c0857fe5"},"schema_version":"1.0","source":{"id":"2212.00006","kind":"arxiv","version":1}},"canonical_sha256":"6dba773dfe812114af60625e913c31313bcdb81f229cdc2a4bc6085098da9de5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dba773dfe812114af60625e913c31313bcdb81f229cdc2a4bc6085098da9de5","first_computed_at":"2026-07-05T05:21:16.821926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:16.821926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRhXJ+zX8Oaoij7vKNQXyPSJjqSsdBn7shbRS7cSTreGjzcg76KKM7dOk2eFtotpTbrAVdASe3GFfmRn5ZMqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:16.822407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb3fb3bd59750e85e048d1fe2f2b5e5c6c87ba507bfb47e8083b596850f5bca6","sha256:6ad316daa16891107d84a087ec1d969937eab155e5cd29a30710a0b23a5f97ec"],"state_sha256":"f4a55fc7cf1ef4e516f97828769fb5269cf18f5e489d510b69a6925d5749b90c"}