{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KH7VMVRAB4RMCZUPQ6YBUT44NE","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":"4a15d87592da47fa18a71445cc81d0edf39b63f4632b26f568b692a6f5a5e4f1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T17:51:40Z","title_canon_sha256":"8f685f8ad9557057d39955e706350f289f90951fa7a3fe4bf845b4d951c0dcfd"},"schema_version":"1.0","source":{"id":"2410.13826","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13826","created_at":"2026-07-05T09:25:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13826v2","created_at":"2026-07-05T09:25:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13826","created_at":"2026-07-05T09:25:20Z"},{"alias_kind":"pith_short_12","alias_value":"KH7VMVRAB4RM","created_at":"2026-07-05T09:25:20Z"},{"alias_kind":"pith_short_16","alias_value":"KH7VMVRAB4RMCZUP","created_at":"2026-07-05T09:25:20Z"},{"alias_kind":"pith_short_8","alias_value":"KH7VMVRA","created_at":"2026-07-05T09:25:20Z"}],"graph_snapshots":[{"event_id":"sha256:b12d164d01a32957e17afa8a12399bec41e6044a887fa678b052fbfb1d38166e","target":"graph","created_at":"2026-07-05T09:25:20Z","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/2410.13826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common acro","authors_text":"Besmira Nushi, Mazda Moayeri, Neel Joshi, Safoora Yousefi, Soheil Feizi, Thomas Fel, Varun Chandrasekaran, Vibhav Vineet, Vidhisha Balachandran","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T17:51:40Z","title":"Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13826","kind":"arxiv","version":2},"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":"sha256:2bc54fc70daa1ea28f1ab37223357a0cce70c5cd6b5f4fa43f5eb5f58d923729","target":"record","created_at":"2026-07-05T09:25:20Z","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":"4a15d87592da47fa18a71445cc81d0edf39b63f4632b26f568b692a6f5a5e4f1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T17:51:40Z","title_canon_sha256":"8f685f8ad9557057d39955e706350f289f90951fa7a3fe4bf845b4d951c0dcfd"},"schema_version":"1.0","source":{"id":"2410.13826","kind":"arxiv","version":2}},"canonical_sha256":"51ff5656200f22c1668f87b01a4f9c6918b5a9e5c05d917ae0f284d4624500b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51ff5656200f22c1668f87b01a4f9c6918b5a9e5c05d917ae0f284d4624500b5","first_computed_at":"2026-07-05T09:25:20.420808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:20.420808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNCkYxOMbXV1DoTXviMRY02ECEkMYqqQA2O/EbF6Q75Z7Oh2TyNn3g/TM/H0kqV9cn0hx0nHFmY7FK8eejgLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:20.421322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13826","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bc54fc70daa1ea28f1ab37223357a0cce70c5cd6b5f4fa43f5eb5f58d923729","sha256:b12d164d01a32957e17afa8a12399bec41e6044a887fa678b052fbfb1d38166e"],"state_sha256":"c0a645f134b7b33785801debd5fe00c07b16f7c2d552540143bb733794a8b791"}