{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M34V7ZSBXJBDJVYVELOX6RWQKQ","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":"6942303525929f855833d75ff8d6c09f7c961600c0bc19dd0fd32c2d6756e247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-01T18:58:42Z","title_canon_sha256":"dfbb8c89626c50d94645f2b459936458baa7b6577b96fd8b9e69461593b1e681"},"schema_version":"1.0","source":{"id":"2401.00849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00849","created_at":"2026-07-05T07:29:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00849v1","created_at":"2026-07-05T07:29:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00849","created_at":"2026-07-05T07:29:23Z"},{"alias_kind":"pith_short_12","alias_value":"M34V7ZSBXJBD","created_at":"2026-07-05T07:29:23Z"},{"alias_kind":"pith_short_16","alias_value":"M34V7ZSBXJBDJVYV","created_at":"2026-07-05T07:29:23Z"},{"alias_kind":"pith_short_8","alias_value":"M34V7ZSB","created_at":"2026-07-05T07:29:23Z"}],"graph_snapshots":[{"event_id":"sha256:ba4245da169622c2df26386c8fff5f8244640660f38437366588feca7342ff14","target":"graph","created_at":"2026-07-05T07:29:23Z","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/2401.00849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the evolution of Vision-Language Pre-training, shifting from short-text comprehension to encompassing extended textual contexts is pivotal. Recent autoregressive vision-language models like \\cite{flamingo, palme}, leveraging the long-context capability of Large Language Models, have excelled in few-shot text generation tasks but face challenges in alignment tasks. Addressing this gap, we introduce the contrastive loss into text generation models, presenting the COntrastive-Streamlined MultimOdal framework (\\ModelName), strategically partitioning the language model into dedicated unimodal te","authors_text":"Alex Jinpeng Wang, Jianfeng Wang, Kevin Lin, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-01T18:58:42Z","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00849","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":"sha256:482a51e24bdd96135ceb2052863b37fde9b23b1307a573dfd3b0b3c5e450f559","target":"record","created_at":"2026-07-05T07:29:23Z","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":"6942303525929f855833d75ff8d6c09f7c961600c0bc19dd0fd32c2d6756e247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-01T18:58:42Z","title_canon_sha256":"dfbb8c89626c50d94645f2b459936458baa7b6577b96fd8b9e69461593b1e681"},"schema_version":"1.0","source":{"id":"2401.00849","kind":"arxiv","version":1}},"canonical_sha256":"66f95fe641ba4234d71522dd7f46d0540603c06d567f46461a5e2cc502e5ee04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66f95fe641ba4234d71522dd7f46d0540603c06d567f46461a5e2cc502e5ee04","first_computed_at":"2026-07-05T07:29:23.596211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:23.596211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cEFYEIwfYAyPYS3AOq9ICNJZt1EPEsngel+y0k2X/rs8chOTLA7//Eofpymn9c3m5Ih6sQt+4+EiScf7uPmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:23.596753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:482a51e24bdd96135ceb2052863b37fde9b23b1307a573dfd3b0b3c5e450f559","sha256:ba4245da169622c2df26386c8fff5f8244640660f38437366588feca7342ff14"],"state_sha256":"f59dbb531cc31fae3b12fdf30edc09cfe36bf20a29743232925b777cc5e95f8f"}