{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YAK2QJBSX4GI33W2YYTM4OK536","short_pith_number":"pith:YAK2QJBS","canonical_record":{"source":{"id":"2308.08428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-16T15:19:52Z","cross_cats_sorted":[],"title_canon_sha256":"bf1c0902056f708a3afc4f546242641e301b660d1a612d5567a534772443e410","abstract_canon_sha256":"dbc56a9153c1139e8e0ac9fc1f31e279eebea141b27a5a33e3fdc60f26db89c3"},"schema_version":"1.0"},"canonical_sha256":"c015a82432bf0c8deedac626ce395ddf8aa749fa2f3ad789d46de6542d3b8138","source":{"kind":"arxiv","id":"2308.08428","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08428","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08428v2","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08428","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"YAK2QJBSX4GI","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"YAK2QJBSX4GI33W2","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"YAK2QJBS","created_at":"2026-07-05T06:42:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YAK2QJBSX4GI33W2YYTM4OK536","target":"record","payload":{"canonical_record":{"source":{"id":"2308.08428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-16T15:19:52Z","cross_cats_sorted":[],"title_canon_sha256":"bf1c0902056f708a3afc4f546242641e301b660d1a612d5567a534772443e410","abstract_canon_sha256":"dbc56a9153c1139e8e0ac9fc1f31e279eebea141b27a5a33e3fdc60f26db89c3"},"schema_version":"1.0"},"canonical_sha256":"c015a82432bf0c8deedac626ce395ddf8aa749fa2f3ad789d46de6542d3b8138","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:25.413356Z","signature_b64":"JiP2OFvM8tZ9k0A3r1aXS9qwcuNDgT6JZvkhqUk41WxcNa2hJ41WPb+MPEIw3Q4uiqbQbAZB6wKgOZo+89nTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c015a82432bf0c8deedac626ce395ddf8aa749fa2f3ad789d46de6542d3b8138","last_reissued_at":"2026-07-05T06:42:25.412927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:25.412927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.08428","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":"2026-07-05T06:42:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"To23Wp6MWtbM9ZSnZKl2RDkTXVx7bGvRC4JN0mI4ARsctPtVqryOG/SZroxw2S3jdoqTG/43XVR9+yRjJdCXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T07:39:09.855782Z"},"content_sha256":"4334ba4dd7f6de52c7fd2bfea044b5e7777b1c2f67919f0f676786cdd6f97f5b","schema_version":"1.0","event_id":"sha256:4334ba4dd7f6de52c7fd2bfea044b5e7777b1c2f67919f0f676786cdd6f97f5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YAK2QJBSX4GI33W2YYTM4OK536","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Guo, Jiankang Deng, Jiawei Li, Jing Yang, Kaicheng Yang, Tongliang Liu, Xiang An, Ziyong Feng","submitted_at":"2023-08-16T15:19:52Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08428","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/2308.08428/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":"2026-07-05T06:42:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FKZzftiJI3qIEN5Yxivoew+0/PeApjNvhdd3jUEJJohRCZXeQGjs/A2ozNMsF5VlJz3DRGrH+VkXfSWVJAmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T07:39:09.856158Z"},"content_sha256":"151c0cfa526647559f8742461637b1788cf410911a5761cde1ad1b0ddd033e1d","schema_version":"1.0","event_id":"sha256:151c0cfa526647559f8742461637b1788cf410911a5761cde1ad1b0ddd033e1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAK2QJBSX4GI33W2YYTM4OK536/bundle.json","state_url":"https://pith.science/pith/YAK2QJBSX4GI33W2YYTM4OK536/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAK2QJBSX4GI33W2YYTM4OK536/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":"2026-07-25T07:39:09Z","links":{"resolver":"https://pith.science/pith/YAK2QJBSX4GI33W2YYTM4OK536","bundle":"https://pith.science/pith/YAK2QJBSX4GI33W2YYTM4OK536/bundle.json","state":"https://pith.science/pith/YAK2QJBSX4GI33W2YYTM4OK536/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAK2QJBSX4GI33W2YYTM4OK536/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YAK2QJBSX4GI33W2YYTM4OK536","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":"dbc56a9153c1139e8e0ac9fc1f31e279eebea141b27a5a33e3fdc60f26db89c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-16T15:19:52Z","title_canon_sha256":"bf1c0902056f708a3afc4f546242641e301b660d1a612d5567a534772443e410"},"schema_version":"1.0","source":{"id":"2308.08428","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08428","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08428v2","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08428","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"YAK2QJBSX4GI","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"YAK2QJBSX4GI33W2","created_at":"2026-07-05T06:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"YAK2QJBS","created_at":"2026-07-05T06:42:25Z"}],"graph_snapshots":[{"event_id":"sha256:151c0cfa526647559f8742461637b1788cf410911a5761cde1ad1b0ddd033e1d","target":"graph","created_at":"2026-07-05T06:42:25Z","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/2308.08428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image","authors_text":"Jia Guo, Jiankang Deng, Jiawei Li, Jing Yang, Kaicheng Yang, Tongliang Liu, Xiang An, Ziyong Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-16T15:19:52Z","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08428","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":"sha256:4334ba4dd7f6de52c7fd2bfea044b5e7777b1c2f67919f0f676786cdd6f97f5b","target":"record","created_at":"2026-07-05T06:42:25Z","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":"dbc56a9153c1139e8e0ac9fc1f31e279eebea141b27a5a33e3fdc60f26db89c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-16T15:19:52Z","title_canon_sha256":"bf1c0902056f708a3afc4f546242641e301b660d1a612d5567a534772443e410"},"schema_version":"1.0","source":{"id":"2308.08428","kind":"arxiv","version":2}},"canonical_sha256":"c015a82432bf0c8deedac626ce395ddf8aa749fa2f3ad789d46de6542d3b8138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c015a82432bf0c8deedac626ce395ddf8aa749fa2f3ad789d46de6542d3b8138","first_computed_at":"2026-07-05T06:42:25.412927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:25.412927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JiP2OFvM8tZ9k0A3r1aXS9qwcuNDgT6JZvkhqUk41WxcNa2hJ41WPb+MPEIw3Q4uiqbQbAZB6wKgOZo+89nTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:25.413356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.08428","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4334ba4dd7f6de52c7fd2bfea044b5e7777b1c2f67919f0f676786cdd6f97f5b","sha256:151c0cfa526647559f8742461637b1788cf410911a5761cde1ad1b0ddd033e1d"],"state_sha256":"b69fa90e5bccec90fc901f851ffd2d94da7a3c03b4523125a3863aa855c55f9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6V+w9DVtKVw38SqQ/w2Mz/ghjhfZB3anWPhtY0l67q3jqxnRBVjJlkridlvqv8RtIk0PoUB6M3Lwl25eWfMhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T07:39:09.858905Z","bundle_sha256":"e8431490279c5e8a91833df46748190c1e61dcf1600967ccfff30d685e293c8a"}}