{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GVUBWLVXBT5BTL7VMXFPJZQL2Y","short_pith_number":"pith:GVUBWLVX","canonical_record":{"source":{"id":"2306.01879","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T19:19:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b8c42682a64873acc7fafdbe88829a9e4e5bd0a6e5ece7c5c92b586e28003264","abstract_canon_sha256":"03b96a90594c99c1c2282d028437027f640cca20f944b2413933eb864eecda42"},"schema_version":"1.0"},"canonical_sha256":"35681b2eb70cfa19aff565caf4e60bd622b335be6081eeec8a43d86496a1f2ea","source":{"kind":"arxiv","id":"2306.01879","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01879","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01879v4","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01879","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"GVUBWLVXBT5B","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"GVUBWLVXBT5BTL7V","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"GVUBWLVX","created_at":"2026-07-05T08:19:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GVUBWLVXBT5BTL7VMXFPJZQL2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01879","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T19:19:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b8c42682a64873acc7fafdbe88829a9e4e5bd0a6e5ece7c5c92b586e28003264","abstract_canon_sha256":"03b96a90594c99c1c2282d028437027f640cca20f944b2413933eb864eecda42"},"schema_version":"1.0"},"canonical_sha256":"35681b2eb70cfa19aff565caf4e60bd622b335be6081eeec8a43d86496a1f2ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:19.435174Z","signature_b64":"hHIC59X/CvAKf+paTMHzbjd2MRFjqkJuG56R3lC8uZjtrjgaT3DIEOZiF+J++4nuu3bouKTCRrUei+JyOqHCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35681b2eb70cfa19aff565caf4e60bd622b335be6081eeec8a43d86496a1f2ea","last_reissued_at":"2026-07-05T08:19:19.434679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:19.434679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01879","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOIMUCZ3GdO9vGAO4jGJOHeBLiNcIaQ6kq+7DItmvA2qDM3E9MMor1Zu5RqTr8dfMXcXilOhANIViGwGEKAAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:02:12.755120Z"},"content_sha256":"a05eef6d2751cea2566fa846d2b7e06cf23558135cf7544b3597ea17907d76f7","schema_version":"1.0","event_id":"sha256:a05eef6d2751cea2566fa846d2b7e06cf23558135cf7544b3597ea17907d76f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GVUBWLVXBT5BTL7VMXFPJZQL2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting the Role of Language Priors in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Deva Ramanan, Pengchuan Zhang, Xinyue Chen, Zhiqiu Lin","submitted_at":"2023-06-02T19:19:43Z","abstract_excerpt":"Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\\textit{generative VLMs}$ that are trained for next-word generation given an image. We explore their zero-shot performance on the illustrative task of image-text retrieval across 8 popular vision-language benchmarks. Our first observation is that they can be repurposed for discriminative tasks (such as image-text retrieval) by simply computing the match score of generating a particular text string given an image. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01879","kind":"arxiv","version":4},"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/2306.01879/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":"2026-07-05T08:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Mp1NCWbOLcJhJ2FzDO/t+96BhOOOoJOx1aVoJ3b0PHLj97014wl/n28UnF4QWpP73CZrugqaxWdXlGNqUgVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:02:12.755625Z"},"content_sha256":"68310e24efa68fbf156e8fb4e4edf1199cff75a70a56894c07fac42d730aa15d","schema_version":"1.0","event_id":"sha256:68310e24efa68fbf156e8fb4e4edf1199cff75a70a56894c07fac42d730aa15d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/bundle.json","state_url":"https://pith.science/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/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":"2026-08-04T17:02:12Z","links":{"resolver":"https://pith.science/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y","bundle":"https://pith.science/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/bundle.json","state":"https://pith.science/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVUBWLVXBT5BTL7VMXFPJZQL2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GVUBWLVXBT5BTL7VMXFPJZQL2Y","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":"03b96a90594c99c1c2282d028437027f640cca20f944b2413933eb864eecda42","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T19:19:43Z","title_canon_sha256":"b8c42682a64873acc7fafdbe88829a9e4e5bd0a6e5ece7c5c92b586e28003264"},"schema_version":"1.0","source":{"id":"2306.01879","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01879","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01879v4","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01879","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"GVUBWLVXBT5B","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"GVUBWLVXBT5BTL7V","created_at":"2026-07-05T08:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"GVUBWLVX","created_at":"2026-07-05T08:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:68310e24efa68fbf156e8fb4e4edf1199cff75a70a56894c07fac42d730aa15d","target":"graph","created_at":"2026-07-05T08:19:19Z","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/2306.01879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\\textit{generative VLMs}$ that are trained for next-word generation given an image. We explore their zero-shot performance on the illustrative task of image-text retrieval across 8 popular vision-language benchmarks. Our first observation is that they can be repurposed for discriminative tasks (such as image-text retrieval) by simply computing the match score of generating a particular text string given an image. W","authors_text":"Deepak Pathak, Deva Ramanan, Pengchuan Zhang, Xinyue Chen, Zhiqiu Lin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T19:19:43Z","title":"Revisiting the Role of Language Priors in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01879","kind":"arxiv","version":4},"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:a05eef6d2751cea2566fa846d2b7e06cf23558135cf7544b3597ea17907d76f7","target":"record","created_at":"2026-07-05T08:19:19Z","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":"03b96a90594c99c1c2282d028437027f640cca20f944b2413933eb864eecda42","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T19:19:43Z","title_canon_sha256":"b8c42682a64873acc7fafdbe88829a9e4e5bd0a6e5ece7c5c92b586e28003264"},"schema_version":"1.0","source":{"id":"2306.01879","kind":"arxiv","version":4}},"canonical_sha256":"35681b2eb70cfa19aff565caf4e60bd622b335be6081eeec8a43d86496a1f2ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35681b2eb70cfa19aff565caf4e60bd622b335be6081eeec8a43d86496a1f2ea","first_computed_at":"2026-07-05T08:19:19.434679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:19.434679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hHIC59X/CvAKf+paTMHzbjd2MRFjqkJuG56R3lC8uZjtrjgaT3DIEOZiF+J++4nuu3bouKTCRrUei+JyOqHCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:19.435174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01879","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a05eef6d2751cea2566fa846d2b7e06cf23558135cf7544b3597ea17907d76f7","sha256:68310e24efa68fbf156e8fb4e4edf1199cff75a70a56894c07fac42d730aa15d"],"state_sha256":"d75ab8bfd5bdea41a49a559d058fa78e08677c3c5c0d5505ffcbd69fa9e8e355"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c3OWK47yUwJOkVT6GYhSdTQ/AW/4EHEJkkNyoWe/NT/Dj4RWRT2kgMk1a5pz1EDoYqUEElvrDX4deqjNDdcjDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:02:12.759804Z","bundle_sha256":"b08a11c520998d54063cd8cb0e23ad031e2861edaa865f83b61d86a9baf2bed4"}}