{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SG7JEMZGD2GJBMQYGIVCO3LLAW","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":"1f25a3262da2281bee76822cd7f442b11640a4e95af6ec3793d7bcb1e872176f","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:35:05Z","title_canon_sha256":"256e2c956cfd8d20d4426178b8754120a31634e13d5ef1002ea9e4c81a6731b6"},"schema_version":"1.0","source":{"id":"2501.16295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16295","created_at":"2026-07-05T10:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16295v1","created_at":"2026-07-05T10:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16295","created_at":"2026-07-05T10:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"SG7JEMZGD2GJ","created_at":"2026-07-05T10:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"SG7JEMZGD2GJBMQY","created_at":"2026-07-05T10:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"SG7JEMZG","created_at":"2026-07-05T10:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:61342765926e6e6f7490b830b51ba4995e8d0b03ce265a1e3c40dfae10b9fdb3","target":"graph","created_at":"2026-07-05T10:05:58Z","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/2501.16295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose Mixture-of-Mamba, a novel SSM architecture that introduces modality-aware sparsity through modality-specific parameterization of the Mamba block. Building on Mixture-of-Transformers (W. Liang et al. arXiv:2411.04996; 2024), we extend the benefits of modality-aware sparsity to SSMs while preserving their computational efficiency. We evaluate Mixture-of-Mamba acros","authors_text":"Genghan Zhang, Junhong Shen, Lili Yu, Luke Zettlemoyer, Ning Dong, Weixin Liang","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:35:05Z","title":"Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16295","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":"sha256:062130be707e57e34d443353080dcc28bbea91eaa9dd257db2667966de6957db","target":"record","created_at":"2026-07-05T10:05:58Z","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":"1f25a3262da2281bee76822cd7f442b11640a4e95af6ec3793d7bcb1e872176f","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:35:05Z","title_canon_sha256":"256e2c956cfd8d20d4426178b8754120a31634e13d5ef1002ea9e4c81a6731b6"},"schema_version":"1.0","source":{"id":"2501.16295","kind":"arxiv","version":1}},"canonical_sha256":"91be9233261e8c90b218322a276d6b05bda5e567a65aab5d1a0dda1752438267","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91be9233261e8c90b218322a276d6b05bda5e567a65aab5d1a0dda1752438267","first_computed_at":"2026-07-05T10:05:58.159523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:58.159523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P2ftgF+I1z2LrNHjxWs86QBVSTUX08LX+d5yZGJhnDp8TgTR2EnGRPVfDTuR5/0+0p8krM7cYGpQQwYgso/xCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:58.160001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:062130be707e57e34d443353080dcc28bbea91eaa9dd257db2667966de6957db","sha256:61342765926e6e6f7490b830b51ba4995e8d0b03ce265a1e3c40dfae10b9fdb3"],"state_sha256":"f7bb9bbbc013f859452b9551c03671abb339be3250a40a7907edb15c5b8f0c16"}