{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SRRMWANSK2VMJG5YWUJ2KOX62Y","short_pith_number":"pith:SRRMWANS","canonical_record":{"source":{"id":"2502.19842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T07:34:42Z","cross_cats_sorted":[],"title_canon_sha256":"9cc96bec8a1e37ef91642d6377cb6b16d41539a6370a54590c41ce9ed29d986a","abstract_canon_sha256":"a6687e1b9690c207357e1cd94fae9aa3aabc6f745298bac5f0ea78c0575ff9ca"},"schema_version":"1.0"},"canonical_sha256":"9462cb01b256aac49bb8b513a53afed609cc38d3858be7b0271b838663c4f36e","source":{"kind":"arxiv","id":"2502.19842","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19842","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19842v2","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19842","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"SRRMWANSK2VM","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"SRRMWANSK2VMJG5Y","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"SRRMWANS","created_at":"2026-07-05T10:22:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SRRMWANSK2VMJG5YWUJ2KOX62Y","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T07:34:42Z","cross_cats_sorted":[],"title_canon_sha256":"9cc96bec8a1e37ef91642d6377cb6b16d41539a6370a54590c41ce9ed29d986a","abstract_canon_sha256":"a6687e1b9690c207357e1cd94fae9aa3aabc6f745298bac5f0ea78c0575ff9ca"},"schema_version":"1.0"},"canonical_sha256":"9462cb01b256aac49bb8b513a53afed609cc38d3858be7b0271b838663c4f36e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:15.562843Z","signature_b64":"DRFx0cQPZyqKk1IeQ2UOOt1EPnKqmEdnTW5g8b4xulYqcr7+kkjh3AcOiL5XIPU4Fyb5F3sJpCSB/CXMcoUOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9462cb01b256aac49bb8b513a53afed609cc38d3858be7b0271b838663c4f36e","last_reissued_at":"2026-07-05T10:22:15.561955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:15.561955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19842","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":"2026-07-05T10:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwAJfeMMECfBlmT9Y0XyFZEChO+YGSCZU3xeEVNajBcufBZ+OzFVI0C5/cMMyVBqNrN9BZ/V9LDO2akZ4xjPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:56:51.807863Z"},"content_sha256":"fbb20e42cb7aa47c793285b612e29e11390768270da594fc35f1c7012e7d68cc","schema_version":"1.0","event_id":"sha256:fbb20e42cb7aa47c793285b612e29e11390768270da594fc35f1c7012e7d68cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SRRMWANSK2VMJG5YWUJ2KOX62Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Nazari, Aminreza Sefid, Mahdieh Soleymani Baghshah, Mohammadali Banayeeanzade, Mohammad Hossein Rohban, Reza Abbasi","submitted_at":"2025-02-27T07:34:42Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a specialized dataset, ComCO, designed to evaluate CLIP's encoders in diverse multi-object scenarios. Our findings reveal significant biases: the text encoder prioritizes first-mentioned objects, and the image encoder favors larger objects. Through retrieval and classification tasks, we quantify these biases across multiple CLIP variants and trace their origins to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19842","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/2502.19842/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":"2026-07-05T10:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWGI/KhIjxgi55S8W/6IE7oaRAhsmj8/Lg2HtLef59e5vwPxNrugQFUJKWZ06iUcfJ3hdDeEDceLfvEzyiRPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:56:51.808228Z"},"content_sha256":"033821796d78aa62837b89de8e9fa929ffecfc0b489f2da1957feebc1cd1d6c1","schema_version":"1.0","event_id":"sha256:033821796d78aa62837b89de8e9fa929ffecfc0b489f2da1957feebc1cd1d6c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/bundle.json","state_url":"https://pith.science/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/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":"2026-07-07T14:56:51Z","links":{"resolver":"https://pith.science/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y","bundle":"https://pith.science/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/bundle.json","state":"https://pith.science/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRRMWANSK2VMJG5YWUJ2KOX62Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SRRMWANSK2VMJG5YWUJ2KOX62Y","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":"a6687e1b9690c207357e1cd94fae9aa3aabc6f745298bac5f0ea78c0575ff9ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T07:34:42Z","title_canon_sha256":"9cc96bec8a1e37ef91642d6377cb6b16d41539a6370a54590c41ce9ed29d986a"},"schema_version":"1.0","source":{"id":"2502.19842","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19842","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19842v2","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19842","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"SRRMWANSK2VM","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"SRRMWANSK2VMJG5Y","created_at":"2026-07-05T10:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"SRRMWANS","created_at":"2026-07-05T10:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:033821796d78aa62837b89de8e9fa929ffecfc0b489f2da1957feebc1cd1d6c1","target":"graph","created_at":"2026-07-05T10:22:15Z","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/2502.19842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a specialized dataset, ComCO, designed to evaluate CLIP's encoders in diverse multi-object scenarios. Our findings reveal significant biases: the text encoder prioritizes first-mentioned objects, and the image encoder favors larger objects. Through retrieval and classification tasks, we quantify these biases across multiple CLIP variants and trace their origins to ","authors_text":"Ali Nazari, Aminreza Sefid, Mahdieh Soleymani Baghshah, Mohammadali Banayeeanzade, Mohammad Hossein Rohban, Reza Abbasi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T07:34:42Z","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19842","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:fbb20e42cb7aa47c793285b612e29e11390768270da594fc35f1c7012e7d68cc","target":"record","created_at":"2026-07-05T10:22:15Z","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":"a6687e1b9690c207357e1cd94fae9aa3aabc6f745298bac5f0ea78c0575ff9ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T07:34:42Z","title_canon_sha256":"9cc96bec8a1e37ef91642d6377cb6b16d41539a6370a54590c41ce9ed29d986a"},"schema_version":"1.0","source":{"id":"2502.19842","kind":"arxiv","version":2}},"canonical_sha256":"9462cb01b256aac49bb8b513a53afed609cc38d3858be7b0271b838663c4f36e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9462cb01b256aac49bb8b513a53afed609cc38d3858be7b0271b838663c4f36e","first_computed_at":"2026-07-05T10:22:15.561955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:15.561955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DRFx0cQPZyqKk1IeQ2UOOt1EPnKqmEdnTW5g8b4xulYqcr7+kkjh3AcOiL5XIPU4Fyb5F3sJpCSB/CXMcoUOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:15.562843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19842","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbb20e42cb7aa47c793285b612e29e11390768270da594fc35f1c7012e7d68cc","sha256:033821796d78aa62837b89de8e9fa929ffecfc0b489f2da1957feebc1cd1d6c1"],"state_sha256":"6ec9843a7a1d7770d11f0de462949400d9f326586a6096c0c411e46760998fc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aYmcUx31X+qMAuyjlfsVjH3QS9B4/68knEnmpx6O13zJ7+UWv1U/hhj5mx/s7h5U8X2E8UcO589OsTvVx1TOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:56:51.810162Z","bundle_sha256":"3f8cd0c63f18dde8114b5d07689a3bc1cb8a7d4c0a831270f9b296c6792f413b"}}