{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZWIU4U4NWY3DHJ7GHWGZEIC5XK","short_pith_number":"pith:ZWIU4U4N","schema_version":"1.0","canonical_sha256":"cd914e538db63633a7e63d8d92205dbabdbbed98b1b3d403e35ada650f744bb5","source":{"kind":"arxiv","id":"1809.02701","version":4},"attestation_state":"computed","paper":{"title":"Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Wallace, Ikuya Yamada, Jordan Boyd-Graber, Pedro Rodriguez, Shi Feng","submitted_at":"2018-09-07T22:39:33Z","abstract_excerpt":"Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human-in-the-loop adversarial generation, where human authors are guided to break models. We aid the authors with interpretations of model predictions through an interactive user interface. We apply this generation framework to a question answering task called Quizbowl, where trivia enthusiasts craft adversarial questions. The resulting questions are validated via live human--co"},"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":"1809.02701","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T22:39:33Z","cross_cats_sorted":[],"title_canon_sha256":"e10a2bcaa4a06e6e9f3c7f5543ec30de26f0ed31bdaa625b692ff6046ab794c4","abstract_canon_sha256":"b1c413b2efee48d76d88cd6a4ee017a4a63b94759fd3445f749b11c723652e21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:34.454467Z","signature_b64":"w0LJjmjM2CXMmerxVhywU55SRGW0m27WvGalPokriwu2PBuQbHqjp9aOGI2m2xx507ErvN7SXFW7r6YrIdMAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd914e538db63633a7e63d8d92205dbabdbbed98b1b3d403e35ada650f744bb5","last_reissued_at":"2026-05-17T23:40:34.454058Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:34.454058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Wallace, Ikuya Yamada, Jordan Boyd-Graber, Pedro Rodriguez, Shi Feng","submitted_at":"2018-09-07T22:39:33Z","abstract_excerpt":"Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human-in-the-loop adversarial generation, where human authors are guided to break models. We aid the authors with interpretations of model predictions through an interactive user interface. We apply this generation framework to a question answering task called Quizbowl, where trivia enthusiasts craft adversarial questions. The resulting questions are validated via live human--co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02701","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.02701","created_at":"2026-05-17T23:40:34.454122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02701v4","created_at":"2026-05-17T23:40:34.454122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02701","created_at":"2026-05-17T23:40:34.454122+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWIU4U4NWY3D","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWIU4U4NWY3DHJ7G","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWIU4U4N","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17922","citing_title":"From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK","json":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK.json","graph_json":"https://pith.science/api/pith-number/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/graph.json","events_json":"https://pith.science/api/pith-number/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/events.json","paper":"https://pith.science/paper/ZWIU4U4N"},"agent_actions":{"view_html":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK","download_json":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK.json","view_paper":"https://pith.science/paper/ZWIU4U4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02701&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/action/storage_attestation","attest_author":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/action/author_attestation","sign_citation":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/action/citation_signature","submit_replication":"https://pith.science/pith/ZWIU4U4NWY3DHJ7GHWGZEIC5XK/action/replication_record"}},"created_at":"2026-05-17T23:40:34.454122+00:00","updated_at":"2026-05-17T23:40:34.454122+00:00"}