{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4TLK2PF52D52STGBV7C6P5XLSK","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":"c0fce5f68104b46f9e3c3f162c4e35aa06a37711dd73088ff0077537edd55364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:34:36Z","title_canon_sha256":"23010d8c3002fa0df3f93fedb9759463d1cd3755639149a25056e8096bea74cb"},"schema_version":"1.0","source":{"id":"2505.14505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14505","created_at":"2026-07-05T11:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14505v1","created_at":"2026-07-05T11:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14505","created_at":"2026-07-05T11:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"4TLK2PF52D52","created_at":"2026-07-05T11:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"4TLK2PF52D52STGB","created_at":"2026-07-05T11:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"4TLK2PF5","created_at":"2026-07-05T11:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:c809c73a7a03b1a6c7a16eae7055f6757660bb280965c89a1d56af1b4e43a68e","target":"graph","created_at":"2026-07-05T11:06:14Z","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/2505.14505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, most multimodal studies are based on large language models (LLMs) with quadratic-complexity Transformer architectures. While linear models like RNNs enjoy low inference costs, their application has been largely limited to the text-only modality. This work explores the capabilities of modern RNN architectures in multimodal contexts. We propose ModRWKV-a decoupled multimodal framework built upon the RWKV7 architecture as its LLM backbone-which achieves multi-source information fusion through dynamically adaptable heterogeneous modality encoders. We designed the multimodal modules in M","authors_text":"Jiale Kang, Jiang Rui, Qingyu Yin, Weile Li, Zening Lu, Zhouran Ji, Ziyin Yue","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:34:36Z","title":"ModRWKV: Transformer Multimodality in Linear Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14505","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:e8c58c737b8236d826763a7f3dd6e6dfa738475511d06fe944b0c19dc455d738","target":"record","created_at":"2026-07-05T11:06:14Z","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":"c0fce5f68104b46f9e3c3f162c4e35aa06a37711dd73088ff0077537edd55364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:34:36Z","title_canon_sha256":"23010d8c3002fa0df3f93fedb9759463d1cd3755639149a25056e8096bea74cb"},"schema_version":"1.0","source":{"id":"2505.14505","kind":"arxiv","version":1}},"canonical_sha256":"e4d6ad3cbdd0fba94cc1afc5e7f6eb92834c6f9a3e20524b98eab437544693c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4d6ad3cbdd0fba94cc1afc5e7f6eb92834c6f9a3e20524b98eab437544693c8","first_computed_at":"2026-07-05T11:06:14.743550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:14.743550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9l++ZOONj2tz5xumgA0v0rrwcG7BsMECASIY9eODSjfWYpBVaFA/v4Zn32nUz4jtASnj011eZqrTSYRLHA+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:14.744059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8c58c737b8236d826763a7f3dd6e6dfa738475511d06fe944b0c19dc455d738","sha256:c809c73a7a03b1a6c7a16eae7055f6757660bb280965c89a1d56af1b4e43a68e"],"state_sha256":"7446ee06588977f92fef7a9c78dfadf9408ad690ca362ab0cf74f9f32f9aa488"}