{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z46ZTLX3JFR6BCKCBP5F3ZTSFS","short_pith_number":"pith:Z46ZTLX3","schema_version":"1.0","canonical_sha256":"cf3d99aefb4963e089420bfa5de6722cbe83835f2287d051d65b162ae094f321","source":{"kind":"arxiv","id":"2505.07704","version":1},"attestation_state":"computed","paper":{"title":"Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander Panchenko, Anton Razzhigaev, Elisei Rykov, Kseniia Petrushina, Kseniia Titova, Vasily Konovalov","submitted_at":"2025-05-12T16:12:11Z","abstract_excerpt":"Measuring how real images look is a complex task in artificial intelligence research. For example, an image of a boy with a vacuum cleaner in a desert violates common sense. We introduce a novel method, which we call Through the Looking Glass (TLG), to assess image common sense consistency using Large Vision-Language Models (LVLMs) and Transformer-based encoder. By leveraging LVLMs to extract atomic facts from these images, we obtain a mix of accurate facts. We proceed by fine-tuning a compact attention-pooling classifier over encoded atomic facts. Our TLG has achieved a new state-of-the-art p"},"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":"2505.07704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T16:12:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bb11f01d74126da97233115628880e71eb5c773ab6413831fa0fff6bb81ca978","abstract_canon_sha256":"0a38a6dc38d19cf48c47bb41f5bdd2fa52f7a40a698c78db85a8a3915bbb5189"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:52.022117Z","signature_b64":"2xamyTtRTAlsKjOoVcJrHNUYJuzIzMOqH+dmUNHGyOmXCcmQ5+xHd67rKfUxab9oSvcG4DLNNrxYUzfKxLWjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3d99aefb4963e089420bfa5de6722cbe83835f2287d051d65b162ae094f321","last_reissued_at":"2026-07-05T11:01:52.021654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:52.021654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander Panchenko, Anton Razzhigaev, Elisei Rykov, Kseniia Petrushina, Kseniia Titova, Vasily Konovalov","submitted_at":"2025-05-12T16:12:11Z","abstract_excerpt":"Measuring how real images look is a complex task in artificial intelligence research. For example, an image of a boy with a vacuum cleaner in a desert violates common sense. We introduce a novel method, which we call Through the Looking Glass (TLG), to assess image common sense consistency using Large Vision-Language Models (LVLMs) and Transformer-based encoder. By leveraging LVLMs to extract atomic facts from these images, we obtain a mix of accurate facts. We proceed by fine-tuning a compact attention-pooling classifier over encoded atomic facts. Our TLG has achieved a new state-of-the-art p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07704","kind":"arxiv","version":1},"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/2505.07704/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":"2505.07704","created_at":"2026-07-05T11:01:52.021711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07704v1","created_at":"2026-07-05T11:01:52.021711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07704","created_at":"2026-07-05T11:01:52.021711+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z46ZTLX3JFR6","created_at":"2026-07-05T11:01:52.021711+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z46ZTLX3JFR6BCKC","created_at":"2026-07-05T11:01:52.021711+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z46ZTLX3","created_at":"2026-07-05T11:01:52.021711+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/Z46ZTLX3JFR6BCKCBP5F3ZTSFS","json":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS.json","graph_json":"https://pith.science/api/pith-number/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/graph.json","events_json":"https://pith.science/api/pith-number/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/events.json","paper":"https://pith.science/paper/Z46ZTLX3"},"agent_actions":{"view_html":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS","download_json":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS.json","view_paper":"https://pith.science/paper/Z46ZTLX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/action/storage_attestation","attest_author":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/action/author_attestation","sign_citation":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/action/citation_signature","submit_replication":"https://pith.science/pith/Z46ZTLX3JFR6BCKCBP5F3ZTSFS/action/replication_record"}},"created_at":"2026-07-05T11:01:52.021711+00:00","updated_at":"2026-07-05T11:01:52.021711+00:00"}