{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HTVBBMCEQD4DHUTGSJLAHWZ4XC","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":"5c81a7bed4559018ee6e665b599565e940476759e83ec9ecf0e16f8cd5dbf3b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:38:21Z","title_canon_sha256":"ad0f018759d57a2d899786ef28c4f53320d77f72d9cbb86d23e49752b0c3d284"},"schema_version":"1.0","source":{"id":"2509.01644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01644","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01644v1","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01644","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"HTVBBMCEQD4D","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"HTVBBMCEQD4DHUTG","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"HTVBBMCE","created_at":"2026-07-05T12:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:570382cfa61c8a81d68dfc0442194a94f8d72a6747b5a3da89ede5004fef6619","target":"graph","created_at":"2026-07-05T12:03:05Z","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/2509.01644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set ","authors_text":"Cihang Xie, Letian Zhang, Xianhang Li, Yanqing Liu, Yuyin Zhou, Zeyu Zheng, Zirui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:38:21Z","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01644","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:d04e7dd7f2e7fcede5088248394cbb2ab448530fa997e6bc51e387185a5767a2","target":"record","created_at":"2026-07-05T12:03:05Z","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":"5c81a7bed4559018ee6e665b599565e940476759e83ec9ecf0e16f8cd5dbf3b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:38:21Z","title_canon_sha256":"ad0f018759d57a2d899786ef28c4f53320d77f72d9cbb86d23e49752b0c3d284"},"schema_version":"1.0","source":{"id":"2509.01644","kind":"arxiv","version":1}},"canonical_sha256":"3cea10b04480f833d266925603db3cb8998a187fa858102ad8d8f8e33dce924f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cea10b04480f833d266925603db3cb8998a187fa858102ad8d8f8e33dce924f","first_computed_at":"2026-07-05T12:03:05.131028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:05.131028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wFw422PrlGYa3gUymyd62CmKWKQ1OFQeUiMlcV6Vg1mbwk++zPbkT4MyOYhAkrpld/cijARM8mV4GhAWbhtUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:05.131607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d04e7dd7f2e7fcede5088248394cbb2ab448530fa997e6bc51e387185a5767a2","sha256:570382cfa61c8a81d68dfc0442194a94f8d72a6747b5a3da89ede5004fef6619"],"state_sha256":"7a5c303ba139711c40291232fd0b6857e69b2ce0ca18a6aa10bb4bc91cd9264f"}