{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EN3UQSBXZ57EBKFSDVBX223I5S","short_pith_number":"pith:EN3UQSBX","canonical_record":{"source":{"id":"2311.18765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:05:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ac6206bd53742a65990710371393521de30871244b23ba4e57a47124dde6e744","abstract_canon_sha256":"db1ed61da36927bcd1536e3e2c89871055b4723df2278d75f68038dcf60b1178"},"schema_version":"1.0"},"canonical_sha256":"2377484837cf7e40a8b21d437d6b68ecbede708046fe4dce0327b38354a3b23c","source":{"kind":"arxiv","id":"2311.18765","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18765","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18765v3","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18765","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"EN3UQSBXZ57E","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"EN3UQSBXZ57EBKFS","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"EN3UQSBX","created_at":"2026-07-05T07:55:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EN3UQSBXZ57EBKFSDVBX223I5S","target":"record","payload":{"canonical_record":{"source":{"id":"2311.18765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:05:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ac6206bd53742a65990710371393521de30871244b23ba4e57a47124dde6e744","abstract_canon_sha256":"db1ed61da36927bcd1536e3e2c89871055b4723df2278d75f68038dcf60b1178"},"schema_version":"1.0"},"canonical_sha256":"2377484837cf7e40a8b21d437d6b68ecbede708046fe4dce0327b38354a3b23c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:26.865465Z","signature_b64":"toNq/PoD2yuVlm4DvOBProz2o/NyIZzzzrbEuxWl+oW1amgltmeD/2k3SJSlSrk5anvXI/v0mw9XX+/41u0JCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2377484837cf7e40a8b21d437d6b68ecbede708046fe4dce0327b38354a3b23c","last_reissued_at":"2026-07-05T07:55:26.864739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:26.864739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.18765","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":"2026-07-05T07:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dzULiCIET6Nm5claNOcqqzuJz/zyUYSWaEqTkKVJ6PKCXpZtwbMqhpjWoYkHc2qBilUsNYZpy2xIkUgxkUBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:41:29.720069Z"},"content_sha256":"ff115ca29d3872eea11f0453387d79fb81e24bb944bd81558f15a4ad6bffa1ae","schema_version":"1.0","event_id":"sha256:ff115ca29d3872eea11f0453387d79fb81e24bb944bd81558f15a4ad6bffa1ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EN3UQSBXZ57EBKFSDVBX223I5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLMs-Augmented Visual-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaipeng Zhang, Kai Wang, Mike Zheng Shou, Ping Luo, Wenqi Shao, Yang You, Yanqing Liu, Yu Qiao","submitted_at":"2023-11-30T18:05:52Z","abstract_excerpt":"Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose \"text shearing\" to maintain the quality and av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18765","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/2311.18765/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":"2026-07-05T07:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35VkZtlDG5x6FNl5WbuKt7F7AXV1u+yHgiXC2qrQotRW2PXUx7ugiLwCvF4XiXXU7xWiW7B6ONNosGGk3GUWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:41:29.720729Z"},"content_sha256":"1091d89f48df922fd70e9dbe9e92197f4cb6be0394e106fc7bd2f24956322441","schema_version":"1.0","event_id":"sha256:1091d89f48df922fd70e9dbe9e92197f4cb6be0394e106fc7bd2f24956322441"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EN3UQSBXZ57EBKFSDVBX223I5S/bundle.json","state_url":"https://pith.science/pith/EN3UQSBXZ57EBKFSDVBX223I5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EN3UQSBXZ57EBKFSDVBX223I5S/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":"2026-07-07T06:41:29Z","links":{"resolver":"https://pith.science/pith/EN3UQSBXZ57EBKFSDVBX223I5S","bundle":"https://pith.science/pith/EN3UQSBXZ57EBKFSDVBX223I5S/bundle.json","state":"https://pith.science/pith/EN3UQSBXZ57EBKFSDVBX223I5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EN3UQSBXZ57EBKFSDVBX223I5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EN3UQSBXZ57EBKFSDVBX223I5S","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":"db1ed61da36927bcd1536e3e2c89871055b4723df2278d75f68038dcf60b1178","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:05:52Z","title_canon_sha256":"ac6206bd53742a65990710371393521de30871244b23ba4e57a47124dde6e744"},"schema_version":"1.0","source":{"id":"2311.18765","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18765","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18765v3","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18765","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"EN3UQSBXZ57E","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"EN3UQSBXZ57EBKFS","created_at":"2026-07-05T07:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"EN3UQSBX","created_at":"2026-07-05T07:55:26Z"}],"graph_snapshots":[{"event_id":"sha256:1091d89f48df922fd70e9dbe9e92197f4cb6be0394e106fc7bd2f24956322441","target":"graph","created_at":"2026-07-05T07:55:26Z","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/2311.18765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose \"text shearing\" to maintain the quality and av","authors_text":"Kaipeng Zhang, Kai Wang, Mike Zheng Shou, Ping Luo, Wenqi Shao, Yang You, Yanqing Liu, Yu Qiao","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:05:52Z","title":"MLLMs-Augmented Visual-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18765","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:ff115ca29d3872eea11f0453387d79fb81e24bb944bd81558f15a4ad6bffa1ae","target":"record","created_at":"2026-07-05T07:55:26Z","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":"db1ed61da36927bcd1536e3e2c89871055b4723df2278d75f68038dcf60b1178","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:05:52Z","title_canon_sha256":"ac6206bd53742a65990710371393521de30871244b23ba4e57a47124dde6e744"},"schema_version":"1.0","source":{"id":"2311.18765","kind":"arxiv","version":3}},"canonical_sha256":"2377484837cf7e40a8b21d437d6b68ecbede708046fe4dce0327b38354a3b23c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2377484837cf7e40a8b21d437d6b68ecbede708046fe4dce0327b38354a3b23c","first_computed_at":"2026-07-05T07:55:26.864739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:26.864739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toNq/PoD2yuVlm4DvOBProz2o/NyIZzzzrbEuxWl+oW1amgltmeD/2k3SJSlSrk5anvXI/v0mw9XX+/41u0JCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:26.865465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18765","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff115ca29d3872eea11f0453387d79fb81e24bb944bd81558f15a4ad6bffa1ae","sha256:1091d89f48df922fd70e9dbe9e92197f4cb6be0394e106fc7bd2f24956322441"],"state_sha256":"6532b9c3da85e27e5445e3f7058d42b2d819fd882f4a1d5ed27382a246eb820c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9jrb5FF+G/aHfgaIIy1AKYpe42L0LP0YW0AKKwQch0TYjgVbZzb8mujicgs+zZJaOeWHEPevaPaBUBHtytdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:41:29.724247Z","bundle_sha256":"ac836dd26ef781d8a78e9781821e9b68dd0316b470f834c370d0adda41c0c7bf"}}