{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HTVBBMCEQD4DHUTGSJLAHWZ4XC","short_pith_number":"pith:HTVBBMCE","canonical_record":{"source":{"id":"2509.01644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"ad0f018759d57a2d899786ef28c4f53320d77f72d9cbb86d23e49752b0c3d284","abstract_canon_sha256":"5c81a7bed4559018ee6e665b599565e940476759e83ec9ecf0e16f8cd5dbf3b1"},"schema_version":"1.0"},"canonical_sha256":"3cea10b04480f833d266925603db3cb8998a187fa858102ad8d8f8e33dce924f","source":{"kind":"arxiv","id":"2509.01644","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HTVBBMCEQD4DHUTGSJLAHWZ4XC","target":"record","payload":{"canonical_record":{"source":{"id":"2509.01644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"ad0f018759d57a2d899786ef28c4f53320d77f72d9cbb86d23e49752b0c3d284","abstract_canon_sha256":"5c81a7bed4559018ee6e665b599565e940476759e83ec9ecf0e16f8cd5dbf3b1"},"schema_version":"1.0"},"canonical_sha256":"3cea10b04480f833d266925603db3cb8998a187fa858102ad8d8f8e33dce924f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:05.131607Z","signature_b64":"wFw422PrlGYa3gUymyd62CmKWKQ1OFQeUiMlcV6Vg1mbwk++zPbkT4MyOYhAkrpld/cijARM8mV4GhAWbhtUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cea10b04480f833d266925603db3cb8998a187fa858102ad8d8f8e33dce924f","last_reissued_at":"2026-07-05T12:03:05.131028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:05.131028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.01644","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVVxLpHbMIRz7C6JEUL6q7WoZM31BeTORO4+ta87Qs/U+pzVfeIDybcFP7+jQ4lpf4wTrfTxiwMJZrPDzCkcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:42:12.374950Z"},"content_sha256":"d04e7dd7f2e7fcede5088248394cbb2ab448530fa997e6bc51e387185a5767a2","schema_version":"1.0","event_id":"sha256:d04e7dd7f2e7fcede5088248394cbb2ab448530fa997e6bc51e387185a5767a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HTVBBMCEQD4DHUTGSJLAHWZ4XC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Letian Zhang, Xianhang Li, Yanqing Liu, Yuyin Zhou, Zeyu Zheng, Zirui Wang","submitted_at":"2025-09-01T17:38:21Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01644","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.01644/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rh38ZT4gCi47dVw0UDmqhjZ4ndeiEtexEq8bBDHEG5VY4w4/sCaoRJpKK6Jh7QUj5FkaEECebWof62yzC3tvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:42:12.375480Z"},"content_sha256":"570382cfa61c8a81d68dfc0442194a94f8d72a6747b5a3da89ede5004fef6619","schema_version":"1.0","event_id":"sha256:570382cfa61c8a81d68dfc0442194a94f8d72a6747b5a3da89ede5004fef6619"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/bundle.json","state_url":"https://pith.science/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T01:42:12Z","links":{"resolver":"https://pith.science/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC","bundle":"https://pith.science/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/bundle.json","state":"https://pith.science/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTVBBMCEQD4DHUTGSJLAHWZ4XC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vncVJipLSVBm9/9J8Q4lFgLwAzG0yFdK/jzKQx54cMeJgJvPD3T6ENwukVw0fewMPxUCiY6hIs37KJtC9T66Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:42:12.381310Z","bundle_sha256":"80d1e4b7f6f4aa4a19b0c83bc27d2a944ec7e74a866060cd7a19bdbe93790e0d"}}