{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KRL2EGAUUL7ZKODNRPWDOMKIHH","short_pith_number":"pith:KRL2EGAU","schema_version":"1.0","canonical_sha256":"5457a21814a2ff95386d8bec37314839cf2144cb23f207745e863ea1d8cb1257","source":{"kind":"arxiv","id":"2310.08577","version":3},"attestation_state":"computed","paper":{"title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Bethge, Max F. Burg, Samuel Albanie, Vishaal Udandarao","submitted_at":"2023-10-12T17:59:30Z","abstract_excerpt":"Recent advances in the development of vision-language models (VLMs) are yielding remarkable success in recognizing visual semantic content, including impressive instances of compositional image understanding. Here, we introduce the novel task of Visual Data-Type Identification, a basic perceptual skill with implications for data curation (e.g., noisy data-removal from large datasets, domain-specific retrieval) and autonomous vision (e.g., distinguishing changing weather conditions from camera lens staining). We develop two datasets consisting of animal images altered across a diverse set of 27"},"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":"2310.08577","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"56bf4d5b8ef5d45d74a1f8f77e191f9b2fc90e5a516a4945747d1012e890be45","abstract_canon_sha256":"c28b808ed38dd6d6089dc2664dd488b5b06753f7c63fb9b2e46ff115a7a01134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:54.311568Z","signature_b64":"nmp3lrCqq5bG5PDYioZ2zz/tfyshx9NcLheV4V4ntbyoZjmRnz27ffOJQS89zEOiseoDrHQa0wTPDQnm7M2IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5457a21814a2ff95386d8bec37314839cf2144cb23f207745e863ea1d8cb1257","last_reissued_at":"2026-07-05T07:20:54.311090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:54.311090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Bethge, Max F. Burg, Samuel Albanie, Vishaal Udandarao","submitted_at":"2023-10-12T17:59:30Z","abstract_excerpt":"Recent advances in the development of vision-language models (VLMs) are yielding remarkable success in recognizing visual semantic content, including impressive instances of compositional image understanding. Here, we introduce the novel task of Visual Data-Type Identification, a basic perceptual skill with implications for data curation (e.g., noisy data-removal from large datasets, domain-specific retrieval) and autonomous vision (e.g., distinguishing changing weather conditions from camera lens staining). We develop two datasets consisting of animal images altered across a diverse set of 27"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08577","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/2310.08577/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":"2310.08577","created_at":"2026-07-05T07:20:54.311148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08577v3","created_at":"2026-07-05T07:20:54.311148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08577","created_at":"2026-07-05T07:20:54.311148+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRL2EGAUUL7Z","created_at":"2026-07-05T07:20:54.311148+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRL2EGAUUL7ZKODN","created_at":"2026-07-05T07:20:54.311148+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRL2EGAU","created_at":"2026-07-05T07:20:54.311148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10442","citing_title":"Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH","json":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH.json","graph_json":"https://pith.science/api/pith-number/KRL2EGAUUL7ZKODNRPWDOMKIHH/graph.json","events_json":"https://pith.science/api/pith-number/KRL2EGAUUL7ZKODNRPWDOMKIHH/events.json","paper":"https://pith.science/paper/KRL2EGAU"},"agent_actions":{"view_html":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH","download_json":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH.json","view_paper":"https://pith.science/paper/KRL2EGAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08577&json=true","fetch_graph":"https://pith.science/api/pith-number/KRL2EGAUUL7ZKODNRPWDOMKIHH/graph.json","fetch_events":"https://pith.science/api/pith-number/KRL2EGAUUL7ZKODNRPWDOMKIHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH/action/storage_attestation","attest_author":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH/action/author_attestation","sign_citation":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH/action/citation_signature","submit_replication":"https://pith.science/pith/KRL2EGAUUL7ZKODNRPWDOMKIHH/action/replication_record"}},"created_at":"2026-07-05T07:20:54.311148+00:00","updated_at":"2026-07-05T07:20:54.311148+00:00"}