{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:42QOG3PVF2VGDSW35AJE3WZVK5","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":"b053b9472c0e365bbafab06d846520d9cef18285e99c3b2f5b9406dda0133553","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T17:00:38Z","title_canon_sha256":"24367f4ec53c0b87e4c275b1da827db8fd21f74640fdd35b820784621c6971e4"},"schema_version":"1.0","source":{"id":"2607.16122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16122","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16122v1","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16122","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"42QOG3PVF2VG","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"42QOG3PVF2VGDSW3","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"42QOG3PV","created_at":"2026-07-20T02:19:34Z"}],"graph_snapshots":[{"event_id":"sha256:383787d9cd9fa53d9cf4b2c6d32f38ed16d68731b1360d2524afff423c564443","target":"graph","created_at":"2026-07-20T02:19:34Z","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/2607.16122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post training data. Most evaluation pipelines identify weak examples, topics, or categories, but they leave the underlying capability failure implicit: they say where a model fails, not why. We introduce CRAFT, a method that converts any rubric based evaluation dataset into a model specific diagnosis of weak capabilities. CRAFT treats each grading criterion as a capability probe: it extracts a capability description from every","authors_text":"Aakash Sabharwal, MohammadHossein Rezaei, Razvan-Gabriel Dumitru, Vipul Gupta, Yunzhong He, Zihao Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T17:00:38Z","title":"CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16122","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:e152218caf809529079f9250878b285a77f93359298a424abec8aeaf1a4683b3","target":"record","created_at":"2026-07-20T02:19:34Z","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":"b053b9472c0e365bbafab06d846520d9cef18285e99c3b2f5b9406dda0133553","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T17:00:38Z","title_canon_sha256":"24367f4ec53c0b87e4c275b1da827db8fd21f74640fdd35b820784621c6971e4"},"schema_version":"1.0","source":{"id":"2607.16122","kind":"arxiv","version":1}},"canonical_sha256":"e6a0e36df52eaa61cadbe8124ddb35574a9535f09b412f0b423e73a9392de6d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6a0e36df52eaa61cadbe8124ddb35574a9535f09b412f0b423e73a9392de6d3","first_computed_at":"2026-07-20T02:19:34.595683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T02:19:34.595683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNPkDPRqM2omFoI1h3BkYXsJmGEUWnynXgk9J2Q6ehIHFOWJTzsQtAVccYjoYvphCHSBuQl1yA3lTlIFPzRWBA==","signature_status":"signed_v1","signed_at":"2026-07-20T02:19:34.596518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e152218caf809529079f9250878b285a77f93359298a424abec8aeaf1a4683b3","sha256:383787d9cd9fa53d9cf4b2c6d32f38ed16d68731b1360d2524afff423c564443"],"state_sha256":"5866831d77004ad461390cf1adea7919df8ba8f8d1ffa3fef21ecaf379c0b151"}