{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QLUDCEOCMHEUULTZSCBOHZGCZQ","short_pith_number":"pith:QLUDCEOC","schema_version":"1.0","canonical_sha256":"82e83111c261c94a2e799082e3e4c2cc2fe91a63be50f16da8876d9f4337cacb","source":{"kind":"arxiv","id":"2405.16277","version":3},"attestation_state":"computed","paper":{"title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Brendan Park, Madeline Janecek, Naser Ezzati-Jivan, Yifeng Li","submitted_at":"2024-05-25T15:28:22Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable success in tasks like the Winograd Schema Challenge (WSC), showcasing advanced textual common-sense reasoning. However, applying this reasoning to multimodal domains, where understanding text and images together is essential, remains a substantial challenge. To address this, we introduce WinoVis, a novel dataset specifically designed to probe text-to-image models on pronoun disambiguation within multimodal contexts. Utilizing GPT-4 for prompt generation and Diffusion Attentive Attribution Maps (DAAM) for heatmap analysis, we propose a n"},"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":"2405.16277","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:28:22Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"bf5a679c211a8428a77cb8204f54d533fc40959382d27923ef3868aa2bb652fd","abstract_canon_sha256":"9d49c4a2d973561a90958d6c4d0cbbc27cac39b00405463214a081231785e432"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:25.737686Z","signature_b64":"C7GcuLINbbCLbh/ENnd2FywO+mHNrdtOSp9+N+lTRrvw9+d2iDMM1fbxDdQ7NSsa9WjQTTOz3gpP9HiioWeWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e83111c261c94a2e799082e3e4c2cc2fe91a63be50f16da8876d9f4337cacb","last_reissued_at":"2026-07-05T08:26:25.737151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:25.737151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Brendan Park, Madeline Janecek, Naser Ezzati-Jivan, Yifeng Li","submitted_at":"2024-05-25T15:28:22Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable success in tasks like the Winograd Schema Challenge (WSC), showcasing advanced textual common-sense reasoning. However, applying this reasoning to multimodal domains, where understanding text and images together is essential, remains a substantial challenge. To address this, we introduce WinoVis, a novel dataset specifically designed to probe text-to-image models on pronoun disambiguation within multimodal contexts. Utilizing GPT-4 for prompt generation and Diffusion Attentive Attribution Maps (DAAM) for heatmap analysis, we propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16277","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/2405.16277/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":"2405.16277","created_at":"2026-07-05T08:26:25.737227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16277v3","created_at":"2026-07-05T08:26:25.737227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16277","created_at":"2026-07-05T08:26:25.737227+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLUDCEOCMHEU","created_at":"2026-07-05T08:26:25.737227+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLUDCEOCMHEUULTZ","created_at":"2026-07-05T08:26:25.737227+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLUDCEOC","created_at":"2026-07-05T08:26:25.737227+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/QLUDCEOCMHEUULTZSCBOHZGCZQ","json":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ.json","graph_json":"https://pith.science/api/pith-number/QLUDCEOCMHEUULTZSCBOHZGCZQ/graph.json","events_json":"https://pith.science/api/pith-number/QLUDCEOCMHEUULTZSCBOHZGCZQ/events.json","paper":"https://pith.science/paper/QLUDCEOC"},"agent_actions":{"view_html":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ","download_json":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ.json","view_paper":"https://pith.science/paper/QLUDCEOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16277&json=true","fetch_graph":"https://pith.science/api/pith-number/QLUDCEOCMHEUULTZSCBOHZGCZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QLUDCEOCMHEUULTZSCBOHZGCZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ/action/storage_attestation","attest_author":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ/action/author_attestation","sign_citation":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ/action/citation_signature","submit_replication":"https://pith.science/pith/QLUDCEOCMHEUULTZSCBOHZGCZQ/action/replication_record"}},"created_at":"2026-07-05T08:26:25.737227+00:00","updated_at":"2026-07-05T08:26:25.737227+00:00"}