{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UVXSPQW3CQHCT2OKFOM724KSJ3","short_pith_number":"pith:UVXSPQW3","canonical_record":{"source":{"id":"2310.20550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T15:31:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e1c895b3c337f73aa101e73411174f3b19bba4f5b86334f5e1cdbfc8f65a9e76","abstract_canon_sha256":"91c1553a7b111a32bc5871187522d49169178ed3f66629d3be8ac7cf8fb8c272"},"schema_version":"1.0"},"canonical_sha256":"a56f27c2db140e29e9ca2b99fd71524eee53d316c32486efa1a10bb5bd39ae84","source":{"kind":"arxiv","id":"2310.20550","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20550","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20550v3","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20550","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"UVXSPQW3CQHC","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"UVXSPQW3CQHCT2OK","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"UVXSPQW3","created_at":"2026-07-05T08:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UVXSPQW3CQHCT2OKFOM724KSJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2310.20550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T15:31:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e1c895b3c337f73aa101e73411174f3b19bba4f5b86334f5e1cdbfc8f65a9e76","abstract_canon_sha256":"91c1553a7b111a32bc5871187522d49169178ed3f66629d3be8ac7cf8fb8c272"},"schema_version":"1.0"},"canonical_sha256":"a56f27c2db140e29e9ca2b99fd71524eee53d316c32486efa1a10bb5bd39ae84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:34.872821Z","signature_b64":"ZTjPUbiwG/yPu8HWsMrXTvY0kPBqYAgfWgv8rp2WoSDp6W5Soi1dEbp/opGy+h+fcHMbbObzCk3nzE03YsyXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56f27c2db140e29e9ca2b99fd71524eee53d316c32486efa1a10bb5bd39ae84","last_reissued_at":"2026-07-05T08:04:34.872299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:34.872299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.20550","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":"2026-07-05T08:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRaVUZlEH7DTnZ3j7qXo+ZUvt46d5NMLy3BZXs2GTAl3Cp62JXv+ZsUlCi9D9JFPUZvBMTScFH5JVatTeX7gDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:22:47.905815Z"},"content_sha256":"f7c6a997adc81d62dcab2dd9f833116535b3bc134344725ded9d35ab77f68dfc","schema_version":"1.0","event_id":"sha256:f7c6a997adc81d62dcab2dd9f833116535b3bc134344725ded9d35ab77f68dfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UVXSPQW3CQHCT2OKFOM724KSJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CapsFusion: Rethinking Image-Text Data at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jingjing Liu, Qiying Yu, Quan Sun, Xiaosong Zhang, Xinlong Wang, Yue Cao, Yufeng Cui","submitted_at":"2023-10-31T15:31:39Z","abstract_excerpt":"Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20550","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/2310.20550/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":"2026-07-05T08:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVSZ8Bd1e9FFVZ3bdw0TaJBDuWL6qerBqLbV5xI8Nv4bDWql83Mbg+LWkGts6lV1BpJR/hBv6ZWFQwxkziLSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:22:47.906774Z"},"content_sha256":"14b906965b3066f95baba769bf329a847ffbd0ae4ab80375cc120b1473b1f088","schema_version":"1.0","event_id":"sha256:14b906965b3066f95baba769bf329a847ffbd0ae4ab80375cc120b1473b1f088"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/bundle.json","state_url":"https://pith.science/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/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":"2026-08-09T15:22:47Z","links":{"resolver":"https://pith.science/pith/UVXSPQW3CQHCT2OKFOM724KSJ3","bundle":"https://pith.science/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/bundle.json","state":"https://pith.science/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVXSPQW3CQHCT2OKFOM724KSJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UVXSPQW3CQHCT2OKFOM724KSJ3","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":"91c1553a7b111a32bc5871187522d49169178ed3f66629d3be8ac7cf8fb8c272","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T15:31:39Z","title_canon_sha256":"e1c895b3c337f73aa101e73411174f3b19bba4f5b86334f5e1cdbfc8f65a9e76"},"schema_version":"1.0","source":{"id":"2310.20550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20550","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20550v3","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20550","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"UVXSPQW3CQHC","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"UVXSPQW3CQHCT2OK","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"UVXSPQW3","created_at":"2026-07-05T08:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:14b906965b3066f95baba769bf329a847ffbd0ae4ab80375cc120b1473b1f088","target":"graph","created_at":"2026-07-05T08:04:34Z","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/2310.20550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we ","authors_text":"Fan Zhang, Jingjing Liu, Qiying Yu, Quan Sun, Xiaosong Zhang, Xinlong Wang, Yue Cao, Yufeng Cui","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T15:31:39Z","title":"CapsFusion: Rethinking Image-Text Data at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20550","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:f7c6a997adc81d62dcab2dd9f833116535b3bc134344725ded9d35ab77f68dfc","target":"record","created_at":"2026-07-05T08:04:34Z","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":"91c1553a7b111a32bc5871187522d49169178ed3f66629d3be8ac7cf8fb8c272","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T15:31:39Z","title_canon_sha256":"e1c895b3c337f73aa101e73411174f3b19bba4f5b86334f5e1cdbfc8f65a9e76"},"schema_version":"1.0","source":{"id":"2310.20550","kind":"arxiv","version":3}},"canonical_sha256":"a56f27c2db140e29e9ca2b99fd71524eee53d316c32486efa1a10bb5bd39ae84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a56f27c2db140e29e9ca2b99fd71524eee53d316c32486efa1a10bb5bd39ae84","first_computed_at":"2026-07-05T08:04:34.872299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:34.872299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZTjPUbiwG/yPu8HWsMrXTvY0kPBqYAgfWgv8rp2WoSDp6W5Soi1dEbp/opGy+h+fcHMbbObzCk3nzE03YsyXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:34.872821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7c6a997adc81d62dcab2dd9f833116535b3bc134344725ded9d35ab77f68dfc","sha256:14b906965b3066f95baba769bf329a847ffbd0ae4ab80375cc120b1473b1f088"],"state_sha256":"148fdfb82eed1f55b43b8a47ae62fd14d7fef190f5caa4da67780b09e6ec57f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6Tz75pUPqLRP3CkAT5xiAXZEcnfvoUjevIRsAP949Ct3ktT5f6vCisxlLLzVVYPJ6dDRfQDBxw6Nc1rN9+wCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:22:47.915416Z","bundle_sha256":"3b52cbbf952e11f7670cc6c7dc38320cdf9756e725c7e5196c801dfc778385de"}}