{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LGKCLSOFCYHVVFAWLQOTYHFBLD","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":"883079dbc073bc84bc29f4716951961068b7c8b9412e3b0cf91cc63bc537b589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-24T18:14:00Z","title_canon_sha256":"14f7e191610cf6eb62e22d39a370a750b99d1e74c66b584738abb1b6c9208078"},"schema_version":"1.0","source":{"id":"2108.10904","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.10904","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2108.10904v3","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10904","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"LGKCLSOFCYHV","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"LGKCLSOFCYHVVFAW","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"LGKCLSOF","created_at":"2026-07-05T04:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:8782c76154c9d3e309bc89ec31b0108f8878a56b8c82e0715030f6529f2bc8d7","target":"graph","created_at":"2026-07-05T04:23:21Z","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/2108.10904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations including clean image captions and regional labels limits the scalability of existing approaches, and complicates the pretraining procedure with the introduction of multiple dataset-specific objectives. In this work, we relax these constraints and present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM). Unlike prior work, SimVLM r","authors_text":"Adams Wei Yu, Jiahui Yu, Yuan Cao, Yulia Tsvetkov, Zihang Dai, Zirui Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-24T18:14:00Z","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10904","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":"sha256:0c74819c56efe4ac7f73859334e430cb454bd420c51527693d69c5018e0dfe65","target":"record","created_at":"2026-07-05T04:23:21Z","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":"883079dbc073bc84bc29f4716951961068b7c8b9412e3b0cf91cc63bc537b589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-24T18:14:00Z","title_canon_sha256":"14f7e191610cf6eb62e22d39a370a750b99d1e74c66b584738abb1b6c9208078"},"schema_version":"1.0","source":{"id":"2108.10904","kind":"arxiv","version":3}},"canonical_sha256":"599425c9c5160f5a94165c1d3c1ca158f2eb5bca31d56ea747bef251e298e970","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599425c9c5160f5a94165c1d3c1ca158f2eb5bca31d56ea747bef251e298e970","first_computed_at":"2026-07-05T04:23:21.390422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:21.390422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hgLczYIzNtkyGamH1lDfpyM62ktvqSRj4GB0pWNr5pkLFeOMkjxB51MhpgeBXE0RQdZJJQLglSB/omvrFOPpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:21.390834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.10904","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c74819c56efe4ac7f73859334e430cb454bd420c51527693d69c5018e0dfe65","sha256:8782c76154c9d3e309bc89ec31b0108f8878a56b8c82e0715030f6529f2bc8d7"],"state_sha256":"6bf5bcc135575fe76e3f22c5ec71470e174be0236f07ad54a142f73ef091d189"}