{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NALMLT5X6QTYLD6CT2T7NVLTNT","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":"406804b05e0209ff9b72f8fdf9193e85f9d9bbefcfdde6464dbf068acdb7ac3a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T00:21:42Z","title_canon_sha256":"f377b5fddf8f2584771c4f9f6130767732accc680e0c7765b58c97f30114f23b"},"schema_version":"1.0","source":{"id":"2110.08420","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08420","created_at":"2026-07-05T10:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08420v3","created_at":"2026-07-05T10:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08420","created_at":"2026-07-05T10:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"NALMLT5X6QTY","created_at":"2026-07-05T10:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"NALMLT5X6QTYLD6C","created_at":"2026-07-05T10:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"NALMLT5X","created_at":"2026-07-05T10:54:28Z"}],"graph_snapshots":[{"event_id":"sha256:fdc1479a8d913db80ff0a382a4985d95c5f0f03c41562ba2089b4296645dd6d7","target":"graph","created_at":"2026-07-05T10:54:28Z","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/2110.08420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimating the difficulty of a dataset typically involves comparing state-of-the-art models to humans; the bigger the performance gap, the harder the dataset is said to be. However, this comparison provides little understanding of how difficult each instance in a given distribution is, or what attributes make the dataset difficult for a given model. To address these questions, we frame dataset difficulty -- w.r.t. a model $\\mathcal{V}$ -- as the lack of $\\mathcal{V}$-$\\textit{usable information}$ (Xu et al., 2019), where a lower value indicates a more difficult dataset for $\\mathcal{V}$. We fu","authors_text":"Kawin Ethayarajh, Swabha Swayamdipta, Yejin Choi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T00:21:42Z","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08420","kind":"arxiv","version":3},"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":"sha256:6d4573e21e7fa123fbc3b205e532ab8cda9078fd2247237edce472ecc167b0d5","target":"record","created_at":"2026-07-05T10:54:28Z","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":"406804b05e0209ff9b72f8fdf9193e85f9d9bbefcfdde6464dbf068acdb7ac3a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T00:21:42Z","title_canon_sha256":"f377b5fddf8f2584771c4f9f6130767732accc680e0c7765b58c97f30114f23b"},"schema_version":"1.0","source":{"id":"2110.08420","kind":"arxiv","version":3}},"canonical_sha256":"6816c5cfb7f427858fc29ea7f6d5736cc7423c3a15573ea6c215fcf14e34ed0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6816c5cfb7f427858fc29ea7f6d5736cc7423c3a15573ea6c215fcf14e34ed0e","first_computed_at":"2026-07-05T10:54:28.689158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:28.689158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H86krPEkHaFUwXrU2AfL7cMxJw2RFhr2yLlFOiaBIqe1OkCggUoxzufGIWNzSF/8JnFN83sHA1hYJt9kEskQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:28.689689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08420","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d4573e21e7fa123fbc3b205e532ab8cda9078fd2247237edce472ecc167b0d5","sha256:fdc1479a8d913db80ff0a382a4985d95c5f0f03c41562ba2089b4296645dd6d7"],"state_sha256":"bd1aa46f35eab9d82f33e031619102b6b566fbbfcf5e80ff03f6196e8bc1c531"}