{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TFGUOKUIJTDBZMJW75MVCWEJZH","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":"89889ac26c4bffa53871f229db2ff3801a6a84886a1b86d3b9a0a9c521db5247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-11T13:28:16Z","title_canon_sha256":"b107d14ea9bffe0be9303cd851fa6eea365f2c933359f169b354eb940f121723"},"schema_version":"1.0","source":{"id":"2607.10308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10308","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10308v1","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10308","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"TFGUOKUIJTDB","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"TFGUOKUIJTDBZMJW","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"TFGUOKUI","created_at":"2026-07-14T01:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:451b7567b2177aef19d92396d4cd93d051d519f2b561e2ef68b64affb57b212e","target":"graph","created_at":"2026-07-14T01:21:08Z","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/2607.10308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the advancements of Large Multimodal Models (LMMs) in RGB vision, their ability to generalize to unseen visual modalities remains a largely unexplored challenge. We argue that different visual modalities are merely distinct samplings of the same physical world. Therefore, effective generalization requires models to possess both modality-agnostic perception of scene semantics and the adaptability to modality-specific characteristics. To achieve this, we propose a training framework, VVM-Tuning, to equip LMMs with these capabilities through modality synthesis and modality contexts. Speci","authors_text":"Ming Liu, Ruyi Zhang, Shihao Yuan, Wangmeng Zuo, Yuanze Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-11T13:28:16Z","title":"Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10308","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":"sha256:5f672a35b335db22209ed136dfb18dc7a17fe14c5389e68983b8aa550057cf1a","target":"record","created_at":"2026-07-14T01:21:08Z","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":"89889ac26c4bffa53871f229db2ff3801a6a84886a1b86d3b9a0a9c521db5247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-11T13:28:16Z","title_canon_sha256":"b107d14ea9bffe0be9303cd851fa6eea365f2c933359f169b354eb940f121723"},"schema_version":"1.0","source":{"id":"2607.10308","kind":"arxiv","version":1}},"canonical_sha256":"994d472a884cc61cb136ff59515889c9e805f3e08b0733604cf9bf91467dbc12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"994d472a884cc61cb136ff59515889c9e805f3e08b0733604cf9bf91467dbc12","first_computed_at":"2026-07-14T01:21:08.726223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:08.726223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aNAfSV5AT2dpodUad87oiNB/By5LgKbjMmTuI2s7iy0xIUhDNNuTAKiVy2XlMFORqH5LMXcp3qpS3ZlTtZu9CA==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:08.727023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f672a35b335db22209ed136dfb18dc7a17fe14c5389e68983b8aa550057cf1a","sha256:451b7567b2177aef19d92396d4cd93d051d519f2b561e2ef68b64affb57b212e"],"state_sha256":"a39fcea34d614dc0362a45e6e7942bdafffdfe5e18f11633ea66db96576d0ab1"}