{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BBJD5Y4GPS5JGJM27V6HEMYZYV","short_pith_number":"pith:BBJD5Y4G","canonical_record":{"source":{"id":"2407.20171","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T17:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"459eee5833165ea95430c0f8745bf90f53bc6df53720806c37ec8b82a79859ce","abstract_canon_sha256":"abc53ae494faaa4f0bca55cb62b6bfebcae91f76d92d44c60ce901b69ac1e2ff"},"schema_version":"1.0"},"canonical_sha256":"08523ee3867cba93259afd7c723319c578813eaf354ac6576498caab460d1df8","source":{"kind":"arxiv","id":"2407.20171","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20171","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20171v4","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20171","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"BBJD5Y4GPS5J","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_16","alias_value":"BBJD5Y4GPS5JGJM2","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_8","alias_value":"BBJD5Y4G","created_at":"2026-07-05T08:58:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BBJD5Y4GPS5JGJM27V6HEMYZYV","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20171","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T17:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"459eee5833165ea95430c0f8745bf90f53bc6df53720806c37ec8b82a79859ce","abstract_canon_sha256":"abc53ae494faaa4f0bca55cb62b6bfebcae91f76d92d44c60ce901b69ac1e2ff"},"schema_version":"1.0"},"canonical_sha256":"08523ee3867cba93259afd7c723319c578813eaf354ac6576498caab460d1df8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:46.367990Z","signature_b64":"1EY5mEx4O7Li4+0V/aFTP42YgQt125XniYzaKmm4xWCxLLi/IKRWcmDkpPbM8TNqq739QDsi3JBWwTaVIGaEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08523ee3867cba93259afd7c723319c578813eaf354ac6576498caab460d1df8","last_reissued_at":"2026-07-05T08:58:46.367541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:46.367541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20171","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":"2026-07-05T08:58:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O4BhxCWsSt2SNKmpsn2Cqrs4+I1/BG+TbrcJmHkIX9/6jXI3D8WwhK4/s9GHQcp0gMbahefZvAjGbtokyQpjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:20:34.026200Z"},"content_sha256":"5d52cbea37d4f2fb10a231cabd40ede1cb794674ef18133f08c83089a74efc20","schema_version":"1.0","event_id":"sha256:5d52cbea37d4f2fb10a231cabd40ede1cb794674ef18133f08c83089a74efc20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BBJD5Y4GPS5JGJM27V6HEMYZYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Feedback Helps CLIP See Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jing Liu, Quan Sun, Wenxuan Wang, Xinlong Wang, Yepeng Tang","submitted_at":"2024-07-29T17:00:09Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that CLIP has severe visual shortcomings, such as which can hardly distinguish orientation, quantity, color, structure, etc. These visual shortcomings also limit the perception capabilities of multimodal large language models (MLLMs) built on CLIP. The main reason could be that the image-text pairs used to train CLIP are inherently biased, due to the lack of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20171","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/2407.20171/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":"2026-07-05T08:58:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tCblPKAc76AHBcPIbPUZTfhrGyC+W6hphYn3bLuclpEkY48peJ1QcNkUQCYtS+/cskOXbb+cktMbN+WELfkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:20:34.026704Z"},"content_sha256":"8fcbd5c0bf0354732e558aa6dc78c9e28a2c02dceae9fc4eb168ec70f863e7aa","schema_version":"1.0","event_id":"sha256:8fcbd5c0bf0354732e558aa6dc78c9e28a2c02dceae9fc4eb168ec70f863e7aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/bundle.json","state_url":"https://pith.science/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/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":"2026-08-12T15:20:34Z","links":{"resolver":"https://pith.science/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV","bundle":"https://pith.science/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/bundle.json","state":"https://pith.science/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBJD5Y4GPS5JGJM27V6HEMYZYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BBJD5Y4GPS5JGJM27V6HEMYZYV","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":"abc53ae494faaa4f0bca55cb62b6bfebcae91f76d92d44c60ce901b69ac1e2ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T17:00:09Z","title_canon_sha256":"459eee5833165ea95430c0f8745bf90f53bc6df53720806c37ec8b82a79859ce"},"schema_version":"1.0","source":{"id":"2407.20171","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20171","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20171v4","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20171","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"BBJD5Y4GPS5J","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_16","alias_value":"BBJD5Y4GPS5JGJM2","created_at":"2026-07-05T08:58:46Z"},{"alias_kind":"pith_short_8","alias_value":"BBJD5Y4G","created_at":"2026-07-05T08:58:46Z"}],"graph_snapshots":[{"event_id":"sha256:8fcbd5c0bf0354732e558aa6dc78c9e28a2c02dceae9fc4eb168ec70f863e7aa","target":"graph","created_at":"2026-07-05T08:58:46Z","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/2407.20171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that CLIP has severe visual shortcomings, such as which can hardly distinguish orientation, quantity, color, structure, etc. These visual shortcomings also limit the perception capabilities of multimodal large language models (MLLMs) built on CLIP. The main reason could be that the image-text pairs used to train CLIP are inherently biased, due to the lack of the ","authors_text":"Fan Zhang, Jing Liu, Quan Sun, Wenxuan Wang, Xinlong Wang, Yepeng Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T17:00:09Z","title":"Diffusion Feedback Helps CLIP See Better"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20171","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":"sha256:5d52cbea37d4f2fb10a231cabd40ede1cb794674ef18133f08c83089a74efc20","target":"record","created_at":"2026-07-05T08:58:46Z","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":"abc53ae494faaa4f0bca55cb62b6bfebcae91f76d92d44c60ce901b69ac1e2ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T17:00:09Z","title_canon_sha256":"459eee5833165ea95430c0f8745bf90f53bc6df53720806c37ec8b82a79859ce"},"schema_version":"1.0","source":{"id":"2407.20171","kind":"arxiv","version":4}},"canonical_sha256":"08523ee3867cba93259afd7c723319c578813eaf354ac6576498caab460d1df8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08523ee3867cba93259afd7c723319c578813eaf354ac6576498caab460d1df8","first_computed_at":"2026-07-05T08:58:46.367541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:46.367541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1EY5mEx4O7Li4+0V/aFTP42YgQt125XniYzaKmm4xWCxLLi/IKRWcmDkpPbM8TNqq739QDsi3JBWwTaVIGaEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:46.367990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20171","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d52cbea37d4f2fb10a231cabd40ede1cb794674ef18133f08c83089a74efc20","sha256:8fcbd5c0bf0354732e558aa6dc78c9e28a2c02dceae9fc4eb168ec70f863e7aa"],"state_sha256":"f05d33351f5afbce6e885de224c834ba38067694ebce8154929e0ceb4ce725c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jfUYJg27shX+NWVbMDI14x8BtnOpe6otDiL12RKdQPYZzB0dVuQByAAhuGsOotoGpvqyejZ2Wquj0pp4K5hCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:20:34.031038Z","bundle_sha256":"1dfe27ede6101960b937a32804120ba2a207c47a0b959c5ef8c91cb9c8555a3b"}}