{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WP57EQKBEWMJBOFR5VQN3LGLVZ","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":"8b46295deb61628ca33282b00f99629864c8ea89267b1697318e6255adb4f741","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T21:18:14Z","title_canon_sha256":"15fcae03bbc25ede3d093411e1d6eb04a793e61a62fe40b47c42e3206e746f97"},"schema_version":"1.0","source":{"id":"2409.00844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00844","created_at":"2026-07-05T09:01:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00844v1","created_at":"2026-07-05T09:01:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00844","created_at":"2026-07-05T09:01:54Z"},{"alias_kind":"pith_short_12","alias_value":"WP57EQKBEWMJ","created_at":"2026-07-05T09:01:54Z"},{"alias_kind":"pith_short_16","alias_value":"WP57EQKBEWMJBOFR","created_at":"2026-07-05T09:01:54Z"},{"alias_kind":"pith_short_8","alias_value":"WP57EQKB","created_at":"2026-07-05T09:01:54Z"}],"graph_snapshots":[{"event_id":"sha256:984500595aaa1f16dff0404509a8d89f0f47cc7c4e14d777e1fa5238d4429bbd","target":"graph","created_at":"2026-07-05T09:01:54Z","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/2409.00844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We propose report cards, which are human-interpretable, natural language summaries of model behavior for specific skills or topics. We develop a framework to evaluate report cards based on three criteria: specificity (ability to distinguish between models), faithfulness (accurate representation of model capabilities), and interpretability (clarity and relevance to humans). We also propose an iterative algorithm for generati","authors_text":"Blair Yang, Fuyang Cui, Jimmy Ba, Keiran Paster, Michael R. Zhang, Pashootan Vaezipoor, Silviu Pitis","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T21:18:14Z","title":"Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00844","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":"sha256:964a1cfdcf5bb33eb5ace14eac353818baa38859ed0fd4e327d0d837c72bb89b","target":"record","created_at":"2026-07-05T09:01:54Z","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":"8b46295deb61628ca33282b00f99629864c8ea89267b1697318e6255adb4f741","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T21:18:14Z","title_canon_sha256":"15fcae03bbc25ede3d093411e1d6eb04a793e61a62fe40b47c42e3206e746f97"},"schema_version":"1.0","source":{"id":"2409.00844","kind":"arxiv","version":1}},"canonical_sha256":"b3fbf24141259890b8b1ed60ddaccbae78f5d26d320450ffcee25e767f95e154","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3fbf24141259890b8b1ed60ddaccbae78f5d26d320450ffcee25e767f95e154","first_computed_at":"2026-07-05T09:01:54.183441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:54.183441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+5oyy406xOlrmCrGCziVmPBC1B2jASWLgZeiajidBxbHYqkdKSDmc3K32SYEKtPL86QfPbutQh9EQrOfJgEOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:54.183901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:964a1cfdcf5bb33eb5ace14eac353818baa38859ed0fd4e327d0d837c72bb89b","sha256:984500595aaa1f16dff0404509a8d89f0f47cc7c4e14d777e1fa5238d4429bbd"],"state_sha256":"35277aaa0867cc818cfefe7606b705ab3e6fc156dbdbed184dcfdcffc3500fd5"}