{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWQO3XCAMRJ5TE7EH7ALM6UEKI","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":"ec09165ffbb4b2457a84c02b88c4944a0c21c63bb3697406c8d84244cbf5da13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:49:02Z","title_canon_sha256":"12b2c7d3a7f1baba9675e4f0f296407e8b85ba3941382e493f171d3a709e637b"},"schema_version":"1.0","source":{"id":"2411.16828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16828","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16828v1","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16828","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"VWQO3XCAMRJ5","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"VWQO3XCAMRJ5TE7E","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"VWQO3XCA","created_at":"2026-07-05T09:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:bacf713f003ddaf839e0a15da301d18fa43fb4c7f912cba520d5bae14a462988","target":"graph","created_at":"2026-07-05T09:40:23Z","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/2411.16828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet effective designs to better leverage richly described synthetic captions. Firstly, by observing a strong inverse effect in learning with synthetic captions -- the short synthetic captions can generally lead to MUCH higher performance than full-length ones -- we therefore fed only partial synthetic captions to the text encoder. Secondly, we incorporate an au","authors_text":"Bingchen Zhao, Cihang Xie, Xianhang Li, Yanqing Liu, Zeyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:49:02Z","title":"CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16828","kind":"arxiv","version":1},"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:ed5efa97485e32baaac137f43f06200186a6d3469545133a7d0c4ec93c413e1d","target":"record","created_at":"2026-07-05T09:40:23Z","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":"ec09165ffbb4b2457a84c02b88c4944a0c21c63bb3697406c8d84244cbf5da13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:49:02Z","title_canon_sha256":"12b2c7d3a7f1baba9675e4f0f296407e8b85ba3941382e493f171d3a709e637b"},"schema_version":"1.0","source":{"id":"2411.16828","kind":"arxiv","version":1}},"canonical_sha256":"ada0eddc406453d993e43fc0b67a8452216f47b00fdffa4444f3360cfdeda32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ada0eddc406453d993e43fc0b67a8452216f47b00fdffa4444f3360cfdeda32c","first_computed_at":"2026-07-05T09:40:23.701828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:23.701828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEZSfwp31ZJjK5Gnsx760nYrC6scvfrCLVgao9Jdzf1WPMSrcHhlggbjxSs+hk+g+9sHPDuzX5NL/0sTKmqLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:23.702321Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed5efa97485e32baaac137f43f06200186a6d3469545133a7d0c4ec93c413e1d","sha256:bacf713f003ddaf839e0a15da301d18fa43fb4c7f912cba520d5bae14a462988"],"state_sha256":"f10b60378a436855cad95289474d6b93684e5437da8480a9427ee0274097cffa"}