{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YPDK7TI5VSSWV7PZLQINRNZHCR","short_pith_number":"pith:YPDK7TI5","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"},"canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","source":{"kind":"arxiv","id":"2210.09996","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09996","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09996v3","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09996","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"YPDK7TI5VSSW","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"YPDK7TI5VSSWV7PZ","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"YPDK7TI5","created_at":"2026-07-05T06:43:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YPDK7TI5VSSWV7PZLQINRNZHCR","target":"record","payload":{"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"},"canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","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"},"source_kind":"arxiv","source_id":"2210.09996","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sghg0ntAh13afH7mcHb/wjnwLIxsaSIBH7HkQIrDrrfrEzgch0LCd87+NWPcdBuYIs3J8d1xo1IzTX1G17rXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T05:44:47.500382Z"},"content_sha256":"c57ef6051b67c26b7c162a7ef454e84c0c70f0214fb72842006c2622fd78a4aa","schema_version":"1.0","event_id":"sha256:c57ef6051b67c26b7c162a7ef454e84c0c70f0214fb72842006c2622fd78a4aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YPDK7TI5VSSWV7PZLQINRNZHCR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqpIpZMXAjxi1mW/HN1XrJQQxXiyCAAuRz5QIzjdZ+3hiCnjFJG7CReuv1gFxPjdsoqpiEaBtjnOSACoogYlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T05:44:47.500760Z"},"content_sha256":"1b07d89943a4629c6be22c4cf59e429f684a857a616fce7adf6f2d0a81332c46","schema_version":"1.0","event_id":"sha256:1b07d89943a4629c6be22c4cf59e429f684a857a616fce7adf6f2d0a81332c46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/bundle.json","state_url":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-20T05:44:47Z","links":{"resolver":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR","bundle":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/bundle.json","state":"https://pith.science/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPDK7TI5VSSWV7PZLQINRNZHCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YPDK7TI5VSSWV7PZLQINRNZHCR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cf654bfaf499e852249ecabf66915f85302595f3257cf0f8ac8fb6a6adadd8f4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T17:01:35Z","title_canon_sha256":"f499f06ee880d1fee3a8d858a6a78e787232b43df52907a19406ac8d99a65469"},"schema_version":"1.0","source":{"id":"2210.09996","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09996","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09996v3","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09996","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"YPDK7TI5VSSW","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"YPDK7TI5VSSWV7PZ","created_at":"2026-07-05T06:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"YPDK7TI5","created_at":"2026-07-05T06:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:1b07d89943a4629c6be22c4cf59e429f684a857a616fce7adf6f2d0a81332c46","target":"graph","created_at":"2026-07-05T06:43:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.09996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Toshev, Brandon McKinzie, Jonathon Shlens, Kanchana Ranasinghe, Sachin Ravi, Yinfei Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T17:01:35Z","title":"Perceptual Grouping in Contrastive Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09996","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c57ef6051b67c26b7c162a7ef454e84c0c70f0214fb72842006c2622fd78a4aa","target":"record","created_at":"2026-07-05T06:43:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cf654bfaf499e852249ecabf66915f85302595f3257cf0f8ac8fb6a6adadd8f4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T17:01:35Z","title_canon_sha256":"f499f06ee880d1fee3a8d858a6a78e787232b43df52907a19406ac8d99a65469"},"schema_version":"1.0","source":{"id":"2210.09996","kind":"arxiv","version":3}},"canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3c6afcd1daca56afdf95c10d8b72714798518caf200c2d2c2d1cf976b736270","first_computed_at":"2026-07-05T06:43:19.618477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:19.618477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vur/EfbBa8R5TwR5i9phxmk5OnL/nt6zl7GKGd9HYcNBP/6FzzqFLMsAR0UcmoE9QIYuVLS+91txi2WjGSPQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:19.618907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09996","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c57ef6051b67c26b7c162a7ef454e84c0c70f0214fb72842006c2622fd78a4aa","sha256:1b07d89943a4629c6be22c4cf59e429f684a857a616fce7adf6f2d0a81332c46"],"state_sha256":"3689670050f4846fb450fd32f5a87192233e5c89f204037a2024b47e9825f9ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ya87Z8V/8MYbEru4IX7VWPQJhasNSfz6ThUq+pIHnbhFvAQJDLh+3LGK0UYt8znv/MmHl5H69oAUGA3E2R3MBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T05:44:47.503276Z","bundle_sha256":"535d244eba90170acb88fe7882a7224f6f981da88e76ce4de5a05086f6268559"}}