{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SBBRV7SIK32J4KVY6WGFPMXKCA","short_pith_number":"pith:SBBRV7SI","canonical_record":{"source":{"id":"2404.07983","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:58:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8cb4b905a7a052eea0e3469cea1e6d41ad9f3d465ed4b3808935b30ebabadae0","abstract_canon_sha256":"285e079dbddfada5e16ef5a2fed4c8f992a8e519a6ab8c316288a0acc09d9e85"},"schema_version":"1.0"},"canonical_sha256":"90431afe4856f49e2ab8f58c57b2ea101e95b7403e1cf68082f3c2e4f82636b1","source":{"kind":"arxiv","id":"2404.07983","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07983","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07983v3","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07983","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"SBBRV7SIK32J","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"SBBRV7SIK32J4KVY","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"SBBRV7SI","created_at":"2026-07-05T10:49:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SBBRV7SIK32J4KVY6WGFPMXKCA","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07983","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:58:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8cb4b905a7a052eea0e3469cea1e6d41ad9f3d465ed4b3808935b30ebabadae0","abstract_canon_sha256":"285e079dbddfada5e16ef5a2fed4c8f992a8e519a6ab8c316288a0acc09d9e85"},"schema_version":"1.0"},"canonical_sha256":"90431afe4856f49e2ab8f58c57b2ea101e95b7403e1cf68082f3c2e4f82636b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:43.938058Z","signature_b64":"ccjnjVHOAS3CpsZvYAAWsBhI3mQYZuAhFVvTXFhtc4eUpggPlSJTE281ZVf6pA9u8alxkZzabifDj7/+eKI9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90431afe4856f49e2ab8f58c57b2ea101e95b7403e1cf68082f3c2e4f82636b1","last_reissued_at":"2026-07-05T10:49:43.937596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:43.937596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07983","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":"2026-07-05T10:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qf0d1AInzZUTWsg8Q29sok/WfZogKUySR9UBxkydnN9R99eA5ZflzIIt4tp3rtcER7WH+xFfARHYMjOsVK+2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:13:01.713852Z"},"content_sha256":"4cee33ad941dc52264eaf4418c53635e7faaddc8cd8121a8584ad8509d0c86d3","schema_version":"1.0","event_id":"sha256:4cee33ad941dc52264eaf4418c53635e7faaddc8cd8121a8584ad8509d0c86d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SBBRV7SIK32J4KVY6WGFPMXKCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance 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":"David T. Hoffmann, Max Argus, Simon Schrodi, Thomas Brox, Volker Fischer","submitted_at":"2024-04-11T17:58:06Z","abstract_excerpt":"Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, like zero-shot object recognition, they perform surprisingly poor on other tasks, like attribute recognition. Previous work has attributed these challenges to the modality gap, a separation of image and text in the shared representation space, and to a bias towards objects over other factors, such as attributes. In this analysis paper, we investigate both phenomena thoroughly. We evaluated off-the-shelf VLMs and while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07983","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/2404.07983/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":"2026-07-05T10:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fq9uBTtovUmKsLxi4mS5+akzGz9/GUre8Msvu2ZQVec1ECKk54+eNPsr2WPY3iZkXkuUskRIQ0nGLYdnqsY0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:13:01.714356Z"},"content_sha256":"7af506a15308eb0d0cb96bb02e9bc9b78431fa82629ae7fa14e12bb03278e1c3","schema_version":"1.0","event_id":"sha256:7af506a15308eb0d0cb96bb02e9bc9b78431fa82629ae7fa14e12bb03278e1c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/bundle.json","state_url":"https://pith.science/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/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":"2026-08-15T08:13:01Z","links":{"resolver":"https://pith.science/pith/SBBRV7SIK32J4KVY6WGFPMXKCA","bundle":"https://pith.science/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/bundle.json","state":"https://pith.science/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBBRV7SIK32J4KVY6WGFPMXKCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SBBRV7SIK32J4KVY6WGFPMXKCA","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":"285e079dbddfada5e16ef5a2fed4c8f992a8e519a6ab8c316288a0acc09d9e85","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:58:06Z","title_canon_sha256":"8cb4b905a7a052eea0e3469cea1e6d41ad9f3d465ed4b3808935b30ebabadae0"},"schema_version":"1.0","source":{"id":"2404.07983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07983","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07983v3","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07983","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"SBBRV7SIK32J","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"SBBRV7SIK32J4KVY","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"SBBRV7SI","created_at":"2026-07-05T10:49:43Z"}],"graph_snapshots":[{"event_id":"sha256:7af506a15308eb0d0cb96bb02e9bc9b78431fa82629ae7fa14e12bb03278e1c3","target":"graph","created_at":"2026-07-05T10:49:43Z","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/2404.07983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, like zero-shot object recognition, they perform surprisingly poor on other tasks, like attribute recognition. Previous work has attributed these challenges to the modality gap, a separation of image and text in the shared representation space, and to a bias towards objects over other factors, such as attributes. In this analysis paper, we investigate both phenomena thoroughly. We evaluated off-the-shelf VLMs and while","authors_text":"David T. Hoffmann, Max Argus, Simon Schrodi, Thomas Brox, Volker Fischer","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:58:06Z","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07983","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":"sha256:4cee33ad941dc52264eaf4418c53635e7faaddc8cd8121a8584ad8509d0c86d3","target":"record","created_at":"2026-07-05T10:49:43Z","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":"285e079dbddfada5e16ef5a2fed4c8f992a8e519a6ab8c316288a0acc09d9e85","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:58:06Z","title_canon_sha256":"8cb4b905a7a052eea0e3469cea1e6d41ad9f3d465ed4b3808935b30ebabadae0"},"schema_version":"1.0","source":{"id":"2404.07983","kind":"arxiv","version":3}},"canonical_sha256":"90431afe4856f49e2ab8f58c57b2ea101e95b7403e1cf68082f3c2e4f82636b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90431afe4856f49e2ab8f58c57b2ea101e95b7403e1cf68082f3c2e4f82636b1","first_computed_at":"2026-07-05T10:49:43.937596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:43.937596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ccjnjVHOAS3CpsZvYAAWsBhI3mQYZuAhFVvTXFhtc4eUpggPlSJTE281ZVf6pA9u8alxkZzabifDj7/+eKI9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:43.938058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cee33ad941dc52264eaf4418c53635e7faaddc8cd8121a8584ad8509d0c86d3","sha256:7af506a15308eb0d0cb96bb02e9bc9b78431fa82629ae7fa14e12bb03278e1c3"],"state_sha256":"b78a525af4cf3b7e0c432b45be6cb410dbf163d0d5af6ce607c831abd2ce72fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PL8QnEpccD6Dt/66nxz1Udt7QZPdzl4xxSv8tI8amnhEB7OYwmZlRWfnktEIwopkwrJMnW5qKBS0QbG5i9KAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:13:01.719229Z","bundle_sha256":"7c3ea58e73cb00c72815f1f330c5e586e87431c66e8d446e7655ac659c683925"}}