{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q767BO3NVILZND3LHG65YCN44N","short_pith_number":"pith:Q767BO3N","schema_version":"1.0","canonical_sha256":"87fdf0bb6daa17968f6b39bddc09bce3710b0107ada01d325cb4cd3243acd38b","source":{"kind":"arxiv","id":"2406.16342","version":3},"attestation_state":"computed","paper":{"title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eve Fleisig, Ishani Mondal, Jordan Lee Boyd-Graber, Maharshi Gor, Yoo Yeon Sung","submitted_at":"2024-06-24T06:27:47Z","abstract_excerpt":"Adversarial datasets should validate AI robustness by providing samples on which humans perform well, but models do not. However, as models evolve, datasets can become obsolete. Measuring whether a dataset remains adversarial is hindered by the lack of a standardized metric for measuring adversarialness. We propose AdvScore, a human-grounded evaluation metric that assesses a dataset's adversarialness by capturing models' and humans' varying abilities while also identifying poor examples. We then use AdvScore to motivate a new dataset creation pipeline for realistic and high-quality adversarial"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.16342","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T06:27:47Z","cross_cats_sorted":[],"title_canon_sha256":"da31e93d9b673680ff59a3d7f677e5a4e9b71fdf87b1ec3d806d01545e17ef5f","abstract_canon_sha256":"80090b7ceca213cbfaaa22ae5dc73f6bfef4cfceef539a642002c14076c3c3f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:34.522601Z","signature_b64":"nDI/4m4bO+TEweIQZYXesN8DqND7eN2nLF+p3LKeumpy452IQg5K/CGXLo1IWxJNgIl3KBN2rovNff/wtoauAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87fdf0bb6daa17968f6b39bddc09bce3710b0107ada01d325cb4cd3243acd38b","last_reissued_at":"2026-07-05T10:16:34.522119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:34.522119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eve Fleisig, Ishani Mondal, Jordan Lee Boyd-Graber, Maharshi Gor, Yoo Yeon Sung","submitted_at":"2024-06-24T06:27:47Z","abstract_excerpt":"Adversarial datasets should validate AI robustness by providing samples on which humans perform well, but models do not. However, as models evolve, datasets can become obsolete. Measuring whether a dataset remains adversarial is hindered by the lack of a standardized metric for measuring adversarialness. We propose AdvScore, a human-grounded evaluation metric that assesses a dataset's adversarialness by capturing models' and humans' varying abilities while also identifying poor examples. We then use AdvScore to motivate a new dataset creation pipeline for realistic and high-quality adversarial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16342","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.16342/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.16342","created_at":"2026-07-05T10:16:34.522177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16342v3","created_at":"2026-07-05T10:16:34.522177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16342","created_at":"2026-07-05T10:16:34.522177+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q767BO3NVILZ","created_at":"2026-07-05T10:16:34.522177+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q767BO3NVILZND3L","created_at":"2026-07-05T10:16:34.522177+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q767BO3N","created_at":"2026-07-05T10:16:34.522177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00741","citing_title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N","json":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N.json","graph_json":"https://pith.science/api/pith-number/Q767BO3NVILZND3LHG65YCN44N/graph.json","events_json":"https://pith.science/api/pith-number/Q767BO3NVILZND3LHG65YCN44N/events.json","paper":"https://pith.science/paper/Q767BO3N"},"agent_actions":{"view_html":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N","download_json":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N.json","view_paper":"https://pith.science/paper/Q767BO3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16342&json=true","fetch_graph":"https://pith.science/api/pith-number/Q767BO3NVILZND3LHG65YCN44N/graph.json","fetch_events":"https://pith.science/api/pith-number/Q767BO3NVILZND3LHG65YCN44N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N/action/storage_attestation","attest_author":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N/action/author_attestation","sign_citation":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N/action/citation_signature","submit_replication":"https://pith.science/pith/Q767BO3NVILZND3LHG65YCN44N/action/replication_record"}},"created_at":"2026-07-05T10:16:34.522177+00:00","updated_at":"2026-07-05T10:16:34.522177+00:00"}