{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JE6QDQYSCCTNQ3K7HRLSYPIXJ5","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":"586964e6e131d9de1889660085d2e0eeabd28c759c46ca7be747d2ced818b8cc","cross_cats_sorted":["cs.CV","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:38:55Z","title_canon_sha256":"9c1b0c0638452708e6f26e4169180d279185c77e9f9bda8ada9b17c2d12f506b"},"schema_version":"1.0","source":{"id":"2008.03964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03964","created_at":"2026-07-05T01:25:58Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03964v1","created_at":"2026-07-05T01:25:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03964","created_at":"2026-07-05T01:25:58Z"},{"alias_kind":"pith_short_12","alias_value":"JE6QDQYSCCTN","created_at":"2026-07-05T01:25:58Z"},{"alias_kind":"pith_short_16","alias_value":"JE6QDQYSCCTNQ3K7","created_at":"2026-07-05T01:25:58Z"},{"alias_kind":"pith_short_8","alias_value":"JE6QDQYS","created_at":"2026-07-05T01:25:58Z"}],"graph_snapshots":[{"event_id":"sha256:bfbc6e6a554379334bbf5218ed4caa6cb740bd6a614d1831e03455fe386f83a5","target":"graph","created_at":"2026-07-05T01:25:58Z","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/2008.03964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A `state of the art' model A surpasses humans in a benchmark B, but fails on similar benchmarks C, D, and E. What does B have that the other benchmarks do not? Recent research provides the answer: spurious bias. However, developing A to solve benchmarks B through E does not guarantee that it will solve future benchmarks. To progress towards a model that `truly learns' an underlying task, we need to quantify the differences between successive benchmarks, as opposed to existing binary and black-box approaches. We propose a novel approach to solve this underexplored task of quantifying benchmark ","authors_text":"Anjana Arunkumar, Bhavdeep Sachdeva, Chitta Baral, Chris Bryan, Swaroop Mishra","cross_cats":["cs.CV","cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:38:55Z","title":"DQI: A Guide to Benchmark Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03964","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":"sha256:3f059acf2ca54cea2ca0d67ca4d01ea9a59dd07eaed33a901b6482ce7bda431c","target":"record","created_at":"2026-07-05T01:25:58Z","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":"586964e6e131d9de1889660085d2e0eeabd28c759c46ca7be747d2ced818b8cc","cross_cats_sorted":["cs.CV","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:38:55Z","title_canon_sha256":"9c1b0c0638452708e6f26e4169180d279185c77e9f9bda8ada9b17c2d12f506b"},"schema_version":"1.0","source":{"id":"2008.03964","kind":"arxiv","version":1}},"canonical_sha256":"493d01c31210a6d86d5f3c572c3d174f68484e9bd0b978b732a6bc65a6b1ca41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"493d01c31210a6d86d5f3c572c3d174f68484e9bd0b978b732a6bc65a6b1ca41","first_computed_at":"2026-07-05T01:25:58.316718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:25:58.316718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OiPba/+acLY7waqGpXOEWUTIUYbtNqOUoCzpyrcEr2RzjuwA3s7CgnEUTT0KkpCJRtKZJJMLg66Px5ZH4jIaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:25:58.317138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f059acf2ca54cea2ca0d67ca4d01ea9a59dd07eaed33a901b6482ce7bda431c","sha256:bfbc6e6a554379334bbf5218ed4caa6cb740bd6a614d1831e03455fe386f83a5"],"state_sha256":"8e99d9643dedd065a2edce12759d4b652711ed08876acce7dbeb71d2c79a7da6"}