{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3M3NDEHV7P3CM7726QMF6D4FV","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":"a72d6dff2004cf1c041ff184b7cb1b0836b61bf15806a96216d24216c7cbc575","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T17:52:47Z","title_canon_sha256":"9216da5eb0e46dd1cb8cab1fc2bac4eed6351777b5855b5c4e95828fbf16e319"},"schema_version":"1.0","source":{"id":"2503.18931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18931","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18931v2","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18931","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3M3NDEHV7P3","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"P3M3NDEHV7P3CM77","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"P3M3NDEH","created_at":"2026-07-05T11:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:5e392eb4c721ec4ca99499827a07d823829a5731e0c28f1e7cd6c84a3cf12d55","target":"graph","created_at":"2026-07-05T11:03:58Z","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/2503.18931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for a wide range of applications. In this paper, we continually pre-train prevailing VFMs in a multimodal manner such that they can effortlessly process visual inputs of varying sizes and produce visual representations that are more aligned with language representations, regardless of their original pre-training process. To this end, we introduce CoMP, a carefully designed multimodal pre-training pipeline. CoMP uses a Continual Rotary Position Embedding to accommodate visual inputs with different resolutions, and","authors_text":"Lingchen Meng, Wujian Peng, Yitong Chen, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T17:52:47Z","title":"CoMP: Continual Multimodal Pre-training for Vision Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18931","kind":"arxiv","version":2},"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:f2358dd1fc89ae59f88c8201a292589ffae03abb0cb3d9855059e75c1f2c2f89","target":"record","created_at":"2026-07-05T11:03:58Z","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":"a72d6dff2004cf1c041ff184b7cb1b0836b61bf15806a96216d24216c7cbc575","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T17:52:47Z","title_canon_sha256":"9216da5eb0e46dd1cb8cab1fc2bac4eed6351777b5855b5c4e95828fbf16e319"},"schema_version":"1.0","source":{"id":"2503.18931","kind":"arxiv","version":2}},"canonical_sha256":"7ed9b68c87afdfb133ffd7a0c2f87c2d6292e627a0af5191d237666a0d99ef67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ed9b68c87afdfb133ffd7a0c2f87c2d6292e627a0af5191d237666a0d99ef67","first_computed_at":"2026-07-05T11:03:58.564823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:58.564823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eKNX8vwY0vuRbuDO1OLyfOULsE6AXNknnN15TxVt6Ch6aFfbdYEXx0n3LSRBiah+Ex5DPuK1BvFnm2GJ3Y6GCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:58.565353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2358dd1fc89ae59f88c8201a292589ffae03abb0cb3d9855059e75c1f2c2f89","sha256:5e392eb4c721ec4ca99499827a07d823829a5731e0c28f1e7cd6c84a3cf12d55"],"state_sha256":"6114e88109bc93d3f7c340515c2c421c1e41393f956659b457848c415f7dd9ae"}