{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ZGNVBKBZWU3U3VQEMBIYGO4RO","short_pith_number":"pith:3ZGNVBKB","schema_version":"1.0","canonical_sha256":"de4cda8541cda9ba6eb023028c19dc8bb065442cf1fd748a48bfb960ffb62681","source":{"kind":"arxiv","id":"2501.13484","version":3},"attestation_state":"computed","paper":{"title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chen Xu, Dawei Yang, Jiangyong Yu, Sifan Zhou, Xing Hu, Yuxuan Yue, Zhihang Yuan, Zhixuan Chen, Zixu Jiang, Zukang Xu","submitted_at":"2025-01-23T08:57:33Z","abstract_excerpt":"Mamba is an efficient sequence model that rivals Transformers and demonstrates significant potential as a foundational architecture for various tasks. Quantization is commonly used in neural networks to reduce model size and computational latency. However, applying quantization to Mamba remains underexplored, and existing quantization methods, which have been effective for CNN and Transformer models, appear inadequate for Mamba models (e.g., Quarot suffers a 21% accuracy drop on Vim-T$^\\dagger$ even under W8A8). We have pioneered the exploration of this issue and identified several key challen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.13484","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T08:57:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ecd651626634fed23b1d36eab697cb31177f2346f197a2a0d9a0093899ee671a","abstract_canon_sha256":"16d28089d78117e90abac1a1e91ac3564fd47fd4de1cf06acf8f39cba0c059b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:33.568391Z","signature_b64":"MfUncv2pQGGXwEhJ8+r4NgT51pEToMfQdex7kXGeSNR71+2wIvUTaZF2nghdKVw6WXYFT/6jFhMRVG7AGuW6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4cda8541cda9ba6eb023028c19dc8bb065442cf1fd748a48bfb960ffb62681","last_reissued_at":"2026-07-05T10:28:33.567828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:33.567828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chen Xu, Dawei Yang, Jiangyong Yu, Sifan Zhou, Xing Hu, Yuxuan Yue, Zhihang Yuan, Zhixuan Chen, Zixu Jiang, Zukang Xu","submitted_at":"2025-01-23T08:57:33Z","abstract_excerpt":"Mamba is an efficient sequence model that rivals Transformers and demonstrates significant potential as a foundational architecture for various tasks. Quantization is commonly used in neural networks to reduce model size and computational latency. However, applying quantization to Mamba remains underexplored, and existing quantization methods, which have been effective for CNN and Transformer models, appear inadequate for Mamba models (e.g., Quarot suffers a 21% accuracy drop on Vim-T$^\\dagger$ even under W8A8). We have pioneered the exploration of this issue and identified several key challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13484","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.13484/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.13484","created_at":"2026-07-05T10:28:33.567895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13484v3","created_at":"2026-07-05T10:28:33.567895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13484","created_at":"2026-07-05T10:28:33.567895+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZGNVBKBZWU3","created_at":"2026-07-05T10:28:33.567895+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZGNVBKBZWU3U3VQ","created_at":"2026-07-05T10:28:33.567895+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZGNVBKB","created_at":"2026-07-05T10:28:33.567895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24019","citing_title":"MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28552","citing_title":"Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10597","citing_title":"COREY: Entropy-Guided Runtime Chunk Scheduling for Selective Scan Kernels","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO","json":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO.json","graph_json":"https://pith.science/api/pith-number/3ZGNVBKBZWU3U3VQEMBIYGO4RO/graph.json","events_json":"https://pith.science/api/pith-number/3ZGNVBKBZWU3U3VQEMBIYGO4RO/events.json","paper":"https://pith.science/paper/3ZGNVBKB"},"agent_actions":{"view_html":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO","download_json":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO.json","view_paper":"https://pith.science/paper/3ZGNVBKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13484&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZGNVBKBZWU3U3VQEMBIYGO4RO/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZGNVBKBZWU3U3VQEMBIYGO4RO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO/action/storage_attestation","attest_author":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO/action/author_attestation","sign_citation":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO/action/citation_signature","submit_replication":"https://pith.science/pith/3ZGNVBKBZWU3U3VQEMBIYGO4RO/action/replication_record"}},"created_at":"2026-07-05T10:28:33.567895+00:00","updated_at":"2026-07-05T10:28:33.567895+00:00"}