{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YPDK7TI5VSSWV7PZLQINRNZHCR","short_pith_number":"pith:YPDK7TI5","schema_version":"1.0","canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","source":{"kind":"arxiv","id":"2210.09996","version":3},"attestation_state":"computed","paper":{"title":"Perceptual Grouping in Contrastive Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Brandon McKinzie, Jonathon Shlens, Kanchana Ranasinghe, Sachin Ravi, Yinfei Yang","submitted_at":"2022-10-18T17:01:35Z","abstract_excerpt":"Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding an image, however, is not just about understanding what content resides within an image, but importantly, where that content resides. In this work we examine how well vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We demonstrate how contemporary vision and language r"},"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":"2210.09996","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T17:01:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f499f06ee880d1fee3a8d858a6a78e787232b43df52907a19406ac8d99a65469","abstract_canon_sha256":"cf654bfaf499e852249ecabf66915f85302595f3257cf0f8ac8fb6a6adadd8f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:19.618907Z","signature_b64":"Vur/EfbBa8R5TwR5i9phxmk5OnL/nt6zl7GKGd9HYcNBP/6FzzqFLMsAR0UcmoE9QIYuVLS+91txi2WjGSPQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","last_reissued_at":"2026-07-05T06:43:19.618477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:19.618477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceptual Grouping in Contrastive Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Brandon McKinzie, Jonathon Shlens, Kanchana Ranasinghe, Sachin Ravi, Yinfei Yang","submitted_at":"2022-10-18T17:01:35Z","abstract_excerpt":"Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding an image, however, is not just about understanding what content resides within an image, but importantly, where that content resides. In this work we examine how well vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We demonstrate how contemporary vision and language r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09996","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/2210.09996/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":"2210.09996","created_at":"2026-07-05T06:43:19.618533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09996v3","created_at":"2026-07-05T06:43:19.618533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09996","created_at":"2026-07-05T06:43:19.618533+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPDK7TI5VSSW","created_at":"2026-07-05T06:43:19.618533+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPDK7TI5VSSWV7PZ","created_at":"2026-07-05T06:43:19.618533+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPDK7TI5","created_at":"2026-07-05T06:43:19.618533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07135","citing_title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR","json":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR.json","graph_json":"https://pith.science/api/pith-number/YPDK7TI5VSSWV7PZLQINRNZHCR/graph.json","events_json":"https://pith.science/api/pith-number/YPDK7TI5VSSWV7PZLQINRNZHCR/events.json","paper":"https://pith.science/paper/YPDK7TI5"},"agent_actions":{"view_html":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR","download_json":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR.json","view_paper":"https://pith.science/paper/YPDK7TI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09996&json=true","fetch_graph":"https://pith.science/api/pith-number/YPDK7TI5VSSWV7PZLQINRNZHCR/graph.json","fetch_events":"https://pith.science/api/pith-number/YPDK7TI5VSSWV7PZLQINRNZHCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/action/storage_attestation","attest_author":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/action/author_attestation","sign_citation":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/action/citation_signature","submit_replication":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/action/replication_record"}},"created_at":"2026-07-05T06:43:19.618533+00:00","updated_at":"2026-07-05T06:43:19.618533+00:00"}