{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UUVPTLZWIEMPOXYCIJO27RK3PT","short_pith_number":"pith:UUVPTLZW","canonical_record":{"source":{"id":"2507.07985","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"df94725869d320d6b04b9e4051b11e63653faab03dadee98b8514d1db8ff0017","abstract_canon_sha256":"53f7aa0cb9ea248e485875b3a0f8428fcd5557628576c1b155936109f53168fa"},"schema_version":"1.0"},"canonical_sha256":"a52af9af364118f75f02425dafc55b7cf9d0b8d36f33db36a628d0a867c43200","source":{"kind":"arxiv","id":"2507.07985","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07985","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07985v2","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07985","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"UUVPTLZWIEMP","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"UUVPTLZWIEMPOXYC","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"UUVPTLZW","created_at":"2026-07-05T11:53:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UUVPTLZWIEMPOXYCIJO27RK3PT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07985","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"df94725869d320d6b04b9e4051b11e63653faab03dadee98b8514d1db8ff0017","abstract_canon_sha256":"53f7aa0cb9ea248e485875b3a0f8428fcd5557628576c1b155936109f53168fa"},"schema_version":"1.0"},"canonical_sha256":"a52af9af364118f75f02425dafc55b7cf9d0b8d36f33db36a628d0a867c43200","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:48.525517Z","signature_b64":"H/V9+0bdRqShwda+b+aRlqoH2BlwzHKtgM0cyAvgEQ/UUptXldBHGEGYSClXV+TKlVe1cp2sBZjuf3n9ney9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a52af9af364118f75f02425dafc55b7cf9d0b8d36f33db36a628d0a867c43200","last_reissued_at":"2026-07-05T11:53:48.525028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:48.525028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07985","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQBmfwQp0ducK49xfC0O4QPb8TBWzfszz2dQkjWe0i58rVrK4SUWb65nlRuYlYTj7gm3ZcwedQmmZ00cQ1ftCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:58:19.787640Z"},"content_sha256":"acca1c07896e4a8996197d56ce977bc3f9b2bb8cc7f25573388dfd00587061e8","schema_version":"1.0","event_id":"sha256:acca1c07896e4a8996197d56ce977bc3f9b2bb8cc7f25573388dfd00587061e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UUVPTLZWIEMPOXYCIJO27RK3PT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Common Data Properties Limit Object-Attribute Binding in CLIP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bijay Gurung, David T. Hoffmann, Thomas Brox","submitted_at":"2025-07-10T17:57:31Z","abstract_excerpt":"Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite their popularity, their representations show major limitations. For instance, CLIP models learn bag-of-words representations and, as a consequence, fail to distinguish whether an image is of ``a yellow submarine and a blue bus'' or ``a blue submarine and a yellow bus''. Previous attempts to fix this issue added hard negatives during training or modified the architecture, but failed to resolve the problem in its entirety"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07985","kind":"arxiv","version":2},"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/2507.07985/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":"2026-07-05T11:53:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1uorha7B6bUF+YmKXsiDS/L4GSyqtNri+BopBr4mrid9qHCQnttxBXbpKJk3LwHRxkKQvbgCsT6z7SN4lbsqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:58:19.788267Z"},"content_sha256":"69fbd8b8cc1dbaaa1811c8969c6d82873d4c22675f0ca4f4dc97274599fcd41f","schema_version":"1.0","event_id":"sha256:69fbd8b8cc1dbaaa1811c8969c6d82873d4c22675f0ca4f4dc97274599fcd41f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/bundle.json","state_url":"https://pith.science/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/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":"2026-08-20T19:58:19Z","links":{"resolver":"https://pith.science/pith/UUVPTLZWIEMPOXYCIJO27RK3PT","bundle":"https://pith.science/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/bundle.json","state":"https://pith.science/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUVPTLZWIEMPOXYCIJO27RK3PT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UUVPTLZWIEMPOXYCIJO27RK3PT","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":"53f7aa0cb9ea248e485875b3a0f8428fcd5557628576c1b155936109f53168fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:57:31Z","title_canon_sha256":"df94725869d320d6b04b9e4051b11e63653faab03dadee98b8514d1db8ff0017"},"schema_version":"1.0","source":{"id":"2507.07985","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07985","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07985v2","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07985","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"UUVPTLZWIEMP","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"UUVPTLZWIEMPOXYC","created_at":"2026-07-05T11:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"UUVPTLZW","created_at":"2026-07-05T11:53:48Z"}],"graph_snapshots":[{"event_id":"sha256:69fbd8b8cc1dbaaa1811c8969c6d82873d4c22675f0ca4f4dc97274599fcd41f","target":"graph","created_at":"2026-07-05T11:53:48Z","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/2507.07985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite their popularity, their representations show major limitations. For instance, CLIP models learn bag-of-words representations and, as a consequence, fail to distinguish whether an image is of ``a yellow submarine and a blue bus'' or ``a blue submarine and a yellow bus''. Previous attempts to fix this issue added hard negatives during training or modified the architecture, but failed to resolve the problem in its entirety","authors_text":"Bijay Gurung, David T. Hoffmann, Thomas Brox","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:57:31Z","title":"Common Data Properties Limit Object-Attribute Binding in CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07985","kind":"arxiv","version":2},"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:acca1c07896e4a8996197d56ce977bc3f9b2bb8cc7f25573388dfd00587061e8","target":"record","created_at":"2026-07-05T11:53:48Z","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":"53f7aa0cb9ea248e485875b3a0f8428fcd5557628576c1b155936109f53168fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:57:31Z","title_canon_sha256":"df94725869d320d6b04b9e4051b11e63653faab03dadee98b8514d1db8ff0017"},"schema_version":"1.0","source":{"id":"2507.07985","kind":"arxiv","version":2}},"canonical_sha256":"a52af9af364118f75f02425dafc55b7cf9d0b8d36f33db36a628d0a867c43200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a52af9af364118f75f02425dafc55b7cf9d0b8d36f33db36a628d0a867c43200","first_computed_at":"2026-07-05T11:53:48.525028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:48.525028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H/V9+0bdRqShwda+b+aRlqoH2BlwzHKtgM0cyAvgEQ/UUptXldBHGEGYSClXV+TKlVe1cp2sBZjuf3n9ney9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:48.525517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07985","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acca1c07896e4a8996197d56ce977bc3f9b2bb8cc7f25573388dfd00587061e8","sha256:69fbd8b8cc1dbaaa1811c8969c6d82873d4c22675f0ca4f4dc97274599fcd41f"],"state_sha256":"750abb45e8bd90ce2dbec7644445aa3bc587bf5c0dd457a9636a2155318cf9ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"keA5DCva0o9PbeNM8Ut6anQKGkgWSN9vAQsY/I1jTTao9khpm6/08t4TMh58IPqymjhNElz1ueP4mdgdNH8uBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T19:58:19.793716Z","bundle_sha256":"74e4b0f8b3eb812eceed413a4868388aff659dd02fb6637c1a8b7b5ffda89c6b"}}