{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4WE6DO75VW7ADL2ZQWTNEVVU3L","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":"9734db327c4e8987285fb862e727bc58cbbe07f717c53e05399dcde3d39bb355","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T12:29:42Z","title_canon_sha256":"0b533c2db32df1bdd5e7b2e8e096386d5f0c45bfec5b0a8d4acd3a373259bfdd"},"schema_version":"1.0","source":{"id":"2306.09085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09085","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09085v1","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09085","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"4WE6DO75VW7A","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"4WE6DO75VW7ADL2Z","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"4WE6DO75","created_at":"2026-07-05T06:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:176644fd91ce9d2d66377f554a35ef3554b5dfc6d5125035dd8a664696b2dfe0","target":"graph","created_at":"2026-07-05T06:21:08Z","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/2306.09085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the limited scale and quality of video-text training corpus, most vision-language foundation models employ image-text datasets for pretraining and primarily focus on modeling visually semantic representations while disregarding temporal semantic representations and correlations. To address this issue, we propose COSA, a COncatenated SAmple pretrained vision-language foundation model. COSA jointly models visual contents and event-level temporal cues using only image-text corpora. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This trans","authors_text":"Handong Li, Jiashi Feng, Jing Liu, Sihan Chen, Xiaojie Jin, Xingjian He","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T12:29:42Z","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09085","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:fdef6f4225f19949223c68b4860442fec836f65eff86e646cba21bf33f678a80","target":"record","created_at":"2026-07-05T06:21:08Z","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":"9734db327c4e8987285fb862e727bc58cbbe07f717c53e05399dcde3d39bb355","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T12:29:42Z","title_canon_sha256":"0b533c2db32df1bdd5e7b2e8e096386d5f0c45bfec5b0a8d4acd3a373259bfdd"},"schema_version":"1.0","source":{"id":"2306.09085","kind":"arxiv","version":1}},"canonical_sha256":"e589e1bbfdadbe01af5985a6d256b4dade76f69f47867fcbb7415a4f8cf2ad59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e589e1bbfdadbe01af5985a6d256b4dade76f69f47867fcbb7415a4f8cf2ad59","first_computed_at":"2026-07-05T06:21:08.414092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:08.414092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CRwXMtmR5vHttrHZf/77HbK0C0lY2RVrWoTgY803uh8fISLINnHhCfpi9heLFLT3FzYSXed6QKZ5Gg5LtzBRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:08.414440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdef6f4225f19949223c68b4860442fec836f65eff86e646cba21bf33f678a80","sha256:176644fd91ce9d2d66377f554a35ef3554b5dfc6d5125035dd8a664696b2dfe0"],"state_sha256":"448870e5cb14d2aa56eeb07334653bc091b59488b6d39ebb674b823d9422cc33"}