{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V5A6TIP3SEF5TNYEE32TIATEGD","short_pith_number":"pith:V5A6TIP3","schema_version":"1.0","canonical_sha256":"af41e9a1fb910bd9b70426f534026430c2f46ea6a8d08342399aa0ab8a50c251","source":{"kind":"arxiv","id":"2504.13439","version":2},"attestation_state":"computed","paper":{"title":"D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grace Byun, Jinho D. Choi","submitted_at":"2025-04-18T03:40:11Z","abstract_excerpt":"Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and labor-intensive. We introduce D-GEN, the first open-source distractor generator model that transforms open-ended data into an MC format. To evaluate distractor quality, we propose two novel methods: (1) ranking alignment, ensuring generated distractors retain the discriminatory power of ground-truth distractors, and (2) entropy analysis, comparing model confidence di"},"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":"2504.13439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T03:40:11Z","cross_cats_sorted":[],"title_canon_sha256":"69b1b019a262f2af2f389761fb57d980ac0c2b9c4e23773dc6c51519c408dabd","abstract_canon_sha256":"9c9cd1d10148ed1947c94edb5b0cbdab1f5cf9de9af0c074be8aa07b76561e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:52.843828Z","signature_b64":"ZsocnvfgFatBL/YmuvoiDXzv/WgXaBQVmc0ZpM8p6HLoj/1rcUFcyEZ24wjRAW9FjGiZcBSERAYIEsTjvOOUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af41e9a1fb910bd9b70426f534026430c2f46ea6a8d08342399aa0ab8a50c251","last_reissued_at":"2026-07-05T11:20:52.843337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:52.843337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grace Byun, Jinho D. Choi","submitted_at":"2025-04-18T03:40:11Z","abstract_excerpt":"Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and labor-intensive. We introduce D-GEN, the first open-source distractor generator model that transforms open-ended data into an MC format. To evaluate distractor quality, we propose two novel methods: (1) ranking alignment, ensuring generated distractors retain the discriminatory power of ground-truth distractors, and (2) entropy analysis, comparing model confidence di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13439","kind":"arxiv","version":2},"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/2504.13439/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":"2504.13439","created_at":"2026-07-05T11:20:52.843397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13439v2","created_at":"2026-07-05T11:20:52.843397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13439","created_at":"2026-07-05T11:20:52.843397+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5A6TIP3SEF5","created_at":"2026-07-05T11:20:52.843397+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5A6TIP3SEF5TNYE","created_at":"2026-07-05T11:20:52.843397+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5A6TIP3","created_at":"2026-07-05T11:20:52.843397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD","json":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD.json","graph_json":"https://pith.science/api/pith-number/V5A6TIP3SEF5TNYEE32TIATEGD/graph.json","events_json":"https://pith.science/api/pith-number/V5A6TIP3SEF5TNYEE32TIATEGD/events.json","paper":"https://pith.science/paper/V5A6TIP3"},"agent_actions":{"view_html":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD","download_json":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD.json","view_paper":"https://pith.science/paper/V5A6TIP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13439&json=true","fetch_graph":"https://pith.science/api/pith-number/V5A6TIP3SEF5TNYEE32TIATEGD/graph.json","fetch_events":"https://pith.science/api/pith-number/V5A6TIP3SEF5TNYEE32TIATEGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD/action/storage_attestation","attest_author":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD/action/author_attestation","sign_citation":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD/action/citation_signature","submit_replication":"https://pith.science/pith/V5A6TIP3SEF5TNYEE32TIATEGD/action/replication_record"}},"created_at":"2026-07-05T11:20:52.843397+00:00","updated_at":"2026-07-05T11:20:52.843397+00:00"}