{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R7FWFJ6MTO6T2427FYWQV3IN6E","short_pith_number":"pith:R7FWFJ6M","canonical_record":{"source":{"id":"2501.00569","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T17:54:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe6372fd8d756a1c288e3aac46b0afdaa8564a10f126fa193cbbfb09a8f922b3","abstract_canon_sha256":"fd8ca77512ac98fce00372667095db0331e52e605cb2dfc8b3517714ae2eabb4"},"schema_version":"1.0"},"canonical_sha256":"8fcb62a7cc9bbd3d735f2e2d0aed0df105954fa0df57892d7eccba9d25f33f6f","source":{"kind":"arxiv","id":"2501.00569","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00569","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00569v4","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00569","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"R7FWFJ6MTO6T","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_16","alias_value":"R7FWFJ6MTO6T2427","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_8","alias_value":"R7FWFJ6M","created_at":"2026-07-05T10:47:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R7FWFJ6MTO6T2427FYWQV3IN6E","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00569","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T17:54:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe6372fd8d756a1c288e3aac46b0afdaa8564a10f126fa193cbbfb09a8f922b3","abstract_canon_sha256":"fd8ca77512ac98fce00372667095db0331e52e605cb2dfc8b3517714ae2eabb4"},"schema_version":"1.0"},"canonical_sha256":"8fcb62a7cc9bbd3d735f2e2d0aed0df105954fa0df57892d7eccba9d25f33f6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:56.771038Z","signature_b64":"1Bg2BPKJAFc4+ErLGIQPkFqxjvuZ+lYdjRWsPxG5bg+V3g1kUL+PhaUtbQCABc6rineW/Eh0vm0+utqfVJKtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fcb62a7cc9bbd3d735f2e2d0aed0df105954fa0df57892d7eccba9d25f33f6f","last_reissued_at":"2026-07-05T10:47:56.770588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:56.770588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00569","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":"2026-07-05T10:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2R8DQ1EzMt0mzu4NkY3/TjMBBqnOVlw6guACdrUaH7VysN9oR7QLPWNhiZpb1qXkXM4CHE0IkE4CHVIsVC/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:53:47.621475Z"},"content_sha256":"66d19121a954735e7a7eb72a422a972fc0a09531454daaf7a295011997f05191","schema_version":"1.0","event_id":"sha256:66d19121a954735e7a7eb72a422a972fc0a09531454daaf7a295011997f05191"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R7FWFJ6MTO6T2427FYWQV3IN6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing Visual Language Priors in VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ang Cao, Gunhee Lee, Honglak Lee, Justin Johnson, Tiange Luo","submitted_at":"2024-12-31T17:54:29Z","abstract_excerpt":"Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring deliberately out-of-distribution images synthesized via image generation models and out-of-distribution Q&A pairs. Each question in ViLP is coupled with three potential answers and three corresponding images: one that can be resolved by text priors alone and two that demand visual reasoning. Although, humans achieve near-perfect accuracy, modern VLMs falter; for ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00569","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/2501.00569/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":"2026-07-05T10:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3g6vH1syvNEP7+LA0SNCoJNFO/Zh+XSvGmvRRuUNnssLcCkZepCJvQnj1H8tPjbclRqp8IhTkGIRQsiYcJPJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:53:47.622038Z"},"content_sha256":"65f353c41fdd8be60ed6edcd5bbc898392a5637226f3b554836db7dcdceb07b6","schema_version":"1.0","event_id":"sha256:65f353c41fdd8be60ed6edcd5bbc898392a5637226f3b554836db7dcdceb07b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/bundle.json","state_url":"https://pith.science/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/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":"2026-08-22T22:53:47Z","links":{"resolver":"https://pith.science/pith/R7FWFJ6MTO6T2427FYWQV3IN6E","bundle":"https://pith.science/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/bundle.json","state":"https://pith.science/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7FWFJ6MTO6T2427FYWQV3IN6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7FWFJ6MTO6T2427FYWQV3IN6E","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":"fd8ca77512ac98fce00372667095db0331e52e605cb2dfc8b3517714ae2eabb4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T17:54:29Z","title_canon_sha256":"fe6372fd8d756a1c288e3aac46b0afdaa8564a10f126fa193cbbfb09a8f922b3"},"schema_version":"1.0","source":{"id":"2501.00569","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00569","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00569v4","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00569","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"R7FWFJ6MTO6T","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_16","alias_value":"R7FWFJ6MTO6T2427","created_at":"2026-07-05T10:47:56Z"},{"alias_kind":"pith_short_8","alias_value":"R7FWFJ6M","created_at":"2026-07-05T10:47:56Z"}],"graph_snapshots":[{"event_id":"sha256:65f353c41fdd8be60ed6edcd5bbc898392a5637226f3b554836db7dcdceb07b6","target":"graph","created_at":"2026-07-05T10:47:56Z","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/2501.00569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring deliberately out-of-distribution images synthesized via image generation models and out-of-distribution Q&A pairs. Each question in ViLP is coupled with three potential answers and three corresponding images: one that can be resolved by text priors alone and two that demand visual reasoning. Although, humans achieve near-perfect accuracy, modern VLMs falter; for ins","authors_text":"Ang Cao, Gunhee Lee, Honglak Lee, Justin Johnson, Tiange Luo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T17:54:29Z","title":"Probing Visual Language Priors in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00569","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":"sha256:66d19121a954735e7a7eb72a422a972fc0a09531454daaf7a295011997f05191","target":"record","created_at":"2026-07-05T10:47:56Z","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":"fd8ca77512ac98fce00372667095db0331e52e605cb2dfc8b3517714ae2eabb4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T17:54:29Z","title_canon_sha256":"fe6372fd8d756a1c288e3aac46b0afdaa8564a10f126fa193cbbfb09a8f922b3"},"schema_version":"1.0","source":{"id":"2501.00569","kind":"arxiv","version":4}},"canonical_sha256":"8fcb62a7cc9bbd3d735f2e2d0aed0df105954fa0df57892d7eccba9d25f33f6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fcb62a7cc9bbd3d735f2e2d0aed0df105954fa0df57892d7eccba9d25f33f6f","first_computed_at":"2026-07-05T10:47:56.770588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:56.770588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Bg2BPKJAFc4+ErLGIQPkFqxjvuZ+lYdjRWsPxG5bg+V3g1kUL+PhaUtbQCABc6rineW/Eh0vm0+utqfVJKtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:56.771038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00569","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d19121a954735e7a7eb72a422a972fc0a09531454daaf7a295011997f05191","sha256:65f353c41fdd8be60ed6edcd5bbc898392a5637226f3b554836db7dcdceb07b6"],"state_sha256":"8cf40189ea691b85144b37b637ebbb2ad71a058f93cee872ad8a4eaa76de6cc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FL56qYpU7KB0iv2ZKzlW5LAvsrqbj0hULA2PACtm/YX1B63UqsV5nYkzoOBVx1MOyoAweAzkh+NaMhNmuqNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:53:47.626478Z","bundle_sha256":"282a6ac81959078ff1f55f81c71e203ae27b0517aaacf92a54f4a284f46c4386"}}