{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZDS5LQIDEAFEAWKOVDA74PWY4P","short_pith_number":"pith:ZDS5LQID","schema_version":"1.0","canonical_sha256":"c8e5d5c103200a40594ea8c1fe3ed8e3dc643694804a6e85abcfc8102178e97a","source":{"kind":"arxiv","id":"2501.13964","version":3},"attestation_state":"computed","paper":{"title":"Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Lin Duan, Maria Gorlatova, Yanming Xiu","submitted_at":"2025-01-21T23:07:03Z","abstract_excerpt":"Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? In this study, we evaluate the capabilities of three state-of-the-art commercial VLMs -- GPT, Gemini, and Claude -- in identifying and describing AR scenes. For this purpose, we use DiverseAR, the first AR data"},"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":"2501.13964","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T23:07:03Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"19b318ff49c261d64406a935d63b3cd468cafc3de0ca89b9840ea8138528e94e","abstract_canon_sha256":"8ed48d087d53899f8211932275f16c80c14039fc1519ef779323dc2a613b5c1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:28.380107Z","signature_b64":"un5BuiSlvlDlQ2eKLap0OdgGCgycgDTzsL07ywOJSGOH/QT/5z+EuCOZBW7QSbDsGOClhd9qpiQn6ftXxz24Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e5d5c103200a40594ea8c1fe3ed8e3dc643694804a6e85abcfc8102178e97a","last_reissued_at":"2026-07-05T10:08:28.379599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:28.379599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Lin Duan, Maria Gorlatova, Yanming Xiu","submitted_at":"2025-01-21T23:07:03Z","abstract_excerpt":"Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? In this study, we evaluate the capabilities of three state-of-the-art commercial VLMs -- GPT, Gemini, and Claude -- in identifying and describing AR scenes. For this purpose, we use DiverseAR, the first AR data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13964","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/2501.13964/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":"2501.13964","created_at":"2026-07-05T10:08:28.379662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13964v3","created_at":"2026-07-05T10:08:28.379662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13964","created_at":"2026-07-05T10:08:28.379662+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDS5LQIDEAFE","created_at":"2026-07-05T10:08:28.379662+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDS5LQIDEAFEAWKO","created_at":"2026-07-05T10:08:28.379662+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDS5LQID","created_at":"2026-07-05T10:08:28.379662+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/ZDS5LQIDEAFEAWKOVDA74PWY4P","json":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P.json","graph_json":"https://pith.science/api/pith-number/ZDS5LQIDEAFEAWKOVDA74PWY4P/graph.json","events_json":"https://pith.science/api/pith-number/ZDS5LQIDEAFEAWKOVDA74PWY4P/events.json","paper":"https://pith.science/paper/ZDS5LQID"},"agent_actions":{"view_html":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P","download_json":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P.json","view_paper":"https://pith.science/paper/ZDS5LQID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13964&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDS5LQIDEAFEAWKOVDA74PWY4P/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDS5LQIDEAFEAWKOVDA74PWY4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P/action/storage_attestation","attest_author":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P/action/author_attestation","sign_citation":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P/action/citation_signature","submit_replication":"https://pith.science/pith/ZDS5LQIDEAFEAWKOVDA74PWY4P/action/replication_record"}},"created_at":"2026-07-05T10:08:28.379662+00:00","updated_at":"2026-07-05T10:08:28.379662+00:00"}