{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KLANPCCUMRWKBGBGHTZ5XEF7JI","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":"5d75028d5d3c4f97ea9cf43f83be591145fc3a57740cb9c5ced388696f255321","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T11:41:55Z","title_canon_sha256":"67f262123538ff5339397348e0a7a4dcdb3590f2c8b806fbb8c76ecac1baa48f"},"schema_version":"1.0","source":{"id":"2410.05938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05938","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05938v1","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05938","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"KLANPCCUMRWK","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"KLANPCCUMRWKBGBG","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"KLANPCCU","created_at":"2026-07-05T09:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:5d938f1f0dc4a63ceb6493c7a709c5580ec28fa493a4babcf276f1b387f59a80","target":"graph","created_at":"2026-07-05T09:17:53Z","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/2410.05938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are insufficient in extracting visual features, leading to imbalanced cross-modal alignment between visual and textural latents, negatively impacting performance on multi-modal tasks. In this work, we propose Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (EMMA), which enables the MLLM to extract fine-grained visual information. Specificall","authors_text":"Dongmei Jiang, Qingfang Zheng, Ruiping Wang, Wenjun Huang, Xiangyuan Lan, Yaowei Wang, Yifei Xing","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T11:41:55Z","title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05938","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":"sha256:6bd37f96c9265578d15cae69f6d6be7ddad751beb01bcae6ba3ef2da81a74b14","target":"record","created_at":"2026-07-05T09:17:53Z","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":"5d75028d5d3c4f97ea9cf43f83be591145fc3a57740cb9c5ced388696f255321","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T11:41:55Z","title_canon_sha256":"67f262123538ff5339397348e0a7a4dcdb3590f2c8b806fbb8c76ecac1baa48f"},"schema_version":"1.0","source":{"id":"2410.05938","kind":"arxiv","version":1}},"canonical_sha256":"52c0d78854646ca098263cf3db90bf4a04b50fb26752a6a2ac1ddf3db5b5a46a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c0d78854646ca098263cf3db90bf4a04b50fb26752a6a2ac1ddf3db5b5a46a","first_computed_at":"2026-07-05T09:17:53.335164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:53.335164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nStrUiBY639N1o1CxnZkwM7NA+aYwJrgwjlT9QHCBqRCW6G3Zk/pAfLNaMfwaMSM6xiBdUh/lQBZVM5Ei824Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:53.335870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bd37f96c9265578d15cae69f6d6be7ddad751beb01bcae6ba3ef2da81a74b14","sha256:5d938f1f0dc4a63ceb6493c7a709c5580ec28fa493a4babcf276f1b387f59a80"],"state_sha256":"dba79495c234bc6b646d015f0ca49790ef325abb1adca8c7eb85663efd33e28f"}