{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6BSPMTN4LSJI3X66IS43KP6BBL","short_pith_number":"pith:6BSPMTN4","schema_version":"1.0","canonical_sha256":"f064f64dbc5c928ddfde44b9b53fc10adfb744a811c9fb8a3b66c796a0b2e943","source":{"kind":"arxiv","id":"2502.09120","version":3},"attestation_state":"computed","paper":{"title":"Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ye-eun Cho, Yunho Maeng","submitted_at":"2025-02-13T09:55:48Z","abstract_excerpt":"This study investigates whether vision-language models (VLMs) can perform pragmatic inference, focusing on ignorance implicatures, utterances that imply the speaker's lack of precise knowledge. To test this, we systematically manipulated contextual cues: the visually depicted situation (visual cue) and QUD-based linguistic prompts (linguistic cue). When only visual cues were provided, three state-of-the-art VLMs (GPT-4o, Gemini 1.5 Pro, and Claude 3.5 sonnet) produced interpretations largely based on the lexical meaning of the modified numerals. When linguistic cues were added to enhance conte"},"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":"2502.09120","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T09:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"4f96a01b148d4ff26babc3e2cdfe2e12d50fc96c0af35ef20c285536927ad959","abstract_canon_sha256":"6b600e378ec9e79c6be5adc5f7b31f76471ea066af03c5979a31f260a3243a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:45.577174Z","signature_b64":"f2ue4WX6BgxSd2066x8gyx2kXcfmeMT2OZNk0jvDcZ3eMI+uxQsbgiXrjD4Gr1JOm/MiiyrBTkRFRt/FPK4ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f064f64dbc5c928ddfde44b9b53fc10adfb744a811c9fb8a3b66c796a0b2e943","last_reissued_at":"2026-07-05T11:04:45.576597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:45.576597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ye-eun Cho, Yunho Maeng","submitted_at":"2025-02-13T09:55:48Z","abstract_excerpt":"This study investigates whether vision-language models (VLMs) can perform pragmatic inference, focusing on ignorance implicatures, utterances that imply the speaker's lack of precise knowledge. To test this, we systematically manipulated contextual cues: the visually depicted situation (visual cue) and QUD-based linguistic prompts (linguistic cue). When only visual cues were provided, three state-of-the-art VLMs (GPT-4o, Gemini 1.5 Pro, and Claude 3.5 sonnet) produced interpretations largely based on the lexical meaning of the modified numerals. When linguistic cues were added to enhance conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09120","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/2502.09120/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":"2502.09120","created_at":"2026-07-05T11:04:45.576664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09120v3","created_at":"2026-07-05T11:04:45.576664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09120","created_at":"2026-07-05T11:04:45.576664+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BSPMTN4LSJI","created_at":"2026-07-05T11:04:45.576664+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BSPMTN4LSJI3X66","created_at":"2026-07-05T11:04:45.576664+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BSPMTN4","created_at":"2026-07-05T11:04:45.576664+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/6BSPMTN4LSJI3X66IS43KP6BBL","json":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL.json","graph_json":"https://pith.science/api/pith-number/6BSPMTN4LSJI3X66IS43KP6BBL/graph.json","events_json":"https://pith.science/api/pith-number/6BSPMTN4LSJI3X66IS43KP6BBL/events.json","paper":"https://pith.science/paper/6BSPMTN4"},"agent_actions":{"view_html":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL","download_json":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL.json","view_paper":"https://pith.science/paper/6BSPMTN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09120&json=true","fetch_graph":"https://pith.science/api/pith-number/6BSPMTN4LSJI3X66IS43KP6BBL/graph.json","fetch_events":"https://pith.science/api/pith-number/6BSPMTN4LSJI3X66IS43KP6BBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL/action/storage_attestation","attest_author":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL/action/author_attestation","sign_citation":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL/action/citation_signature","submit_replication":"https://pith.science/pith/6BSPMTN4LSJI3X66IS43KP6BBL/action/replication_record"}},"created_at":"2026-07-05T11:04:45.576664+00:00","updated_at":"2026-07-05T11:04:45.576664+00:00"}