{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DNKSUGZVW6QRAMY7S42SVDNA6F","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":"3cd55199acd0f73efd874c949cd4b02931d77807581fbba95343634f58091784","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T06:41:00Z","title_canon_sha256":"c2cea8b7449aab276c8d0da647626191ea335d3a35db3dd5a28b33b46e2ba216"},"schema_version":"1.0","source":{"id":"2506.23115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23115","created_at":"2026-07-05T11:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23115v1","created_at":"2026-07-05T11:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23115","created_at":"2026-07-05T11:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"DNKSUGZVW6QR","created_at":"2026-07-05T11:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"DNKSUGZVW6QRAMY7","created_at":"2026-07-05T11:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"DNKSUGZV","created_at":"2026-07-05T11:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:e305c67f65c1d325c70f45e8f725c760e2e02513d2dc3ecdca70b9b3e1821a04","target":"graph","created_at":"2026-07-05T11:29:15Z","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/2506.23115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for embedding tasks; scalability issues due to reliance on high-quality labeled paired data for contrastive learning; and limited diversity in training objectives and data. To address these issues, we propose MoCa, a two-stage framework for transforming pre-trained VLMs into effective bidirectional multimodal embedding models. The first stage, Modality-aware Continual","authors_text":"Furu Wei, Haonan Chen, Hong Liu, Liang Wang, Nan Yang, Yuping Luo, Zhicheng Dou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T06:41:00Z","title":"MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23115","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":"sha256:7fb56146881ab012324d4ff6c9798006ba43dbfdd02743b83ee9365aa6c1691d","target":"record","created_at":"2026-07-05T11:29:15Z","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":"3cd55199acd0f73efd874c949cd4b02931d77807581fbba95343634f58091784","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T06:41:00Z","title_canon_sha256":"c2cea8b7449aab276c8d0da647626191ea335d3a35db3dd5a28b33b46e2ba216"},"schema_version":"1.0","source":{"id":"2506.23115","kind":"arxiv","version":1}},"canonical_sha256":"1b552a1b35b7a110331f97352a8da0f158e708038f9ead7d1bd639846c7d2926","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b552a1b35b7a110331f97352a8da0f158e708038f9ead7d1bd639846c7d2926","first_computed_at":"2026-07-05T11:29:15.902036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:15.902036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VW5bASJuF+Zip99oQTRK0TKyuB9KkbmS9jwNeuSQwAPv6/F/3ocoTEnstjX9k1wLwR1MVrPZiLVWiJkcHyjxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:15.902574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fb56146881ab012324d4ff6c9798006ba43dbfdd02743b83ee9365aa6c1691d","sha256:e305c67f65c1d325c70f45e8f725c760e2e02513d2dc3ecdca70b9b3e1821a04"],"state_sha256":"ae6e7aa2617eef7ce2a95cbfd8797763c93ec7b389dd6feb2ba897004675883f"}