{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WVUXSWOQ2IAZ5CBATTAA5T5HK7","short_pith_number":"pith:WVUXSWOQ","schema_version":"1.0","canonical_sha256":"b5697959d0d2019e88209cc00ecfa757cb4d0e88d407260db3436e5253a668a2","source":{"kind":"arxiv","id":"2410.13229","version":2},"attestation_state":"computed","paper":{"title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi-Chih Chang, Diana Marculescu, Hung-Yueh Chiang, Kai-Chiang Wu, Natalia Frumkin","submitted_at":"2024-10-17T05:32:33Z","abstract_excerpt":"State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than attention-based networks. The superior computational efficiency of SSMs in long sequence modeling positions them favorably over Transformers in many scenarios. However, improving the efficiency of SSMs on request-intensive cloud-serving and resource-limited edge applications is still a formidable task. SSM quantization is a possible solution to this problem, making S"},"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":"2410.13229","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T05:32:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19835aaa4ff54a9ff32603d66b0cc481499ec28988cf1478eac4450c70362a70","abstract_canon_sha256":"09d478f99964d2012b350f99c997f14f3caa6f3cae9f2fd61d6aef3492cea0e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:56.370045Z","signature_b64":"e/ygv15Kr87DCmj0sjKHnIVVOsBMc/jv6dOKsvP3sMyLUBwwlwuFX6v1DTMm5EGl4+S2bjw1ihXPTKzX/CI2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5697959d0d2019e88209cc00ecfa757cb4d0e88d407260db3436e5253a668a2","last_reissued_at":"2026-07-05T09:45:56.369577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:56.369577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi-Chih Chang, Diana Marculescu, Hung-Yueh Chiang, Kai-Chiang Wu, Natalia Frumkin","submitted_at":"2024-10-17T05:32:33Z","abstract_excerpt":"State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than attention-based networks. The superior computational efficiency of SSMs in long sequence modeling positions them favorably over Transformers in many scenarios. However, improving the efficiency of SSMs on request-intensive cloud-serving and resource-limited edge applications is still a formidable task. SSM quantization is a possible solution to this problem, making S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13229","kind":"arxiv","version":2},"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/2410.13229/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":"2410.13229","created_at":"2026-07-05T09:45:56.369630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13229v2","created_at":"2026-07-05T09:45:56.369630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13229","created_at":"2026-07-05T09:45:56.369630+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVUXSWOQ2IAZ","created_at":"2026-07-05T09:45:56.369630+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVUXSWOQ2IAZ5CBA","created_at":"2026-07-05T09:45:56.369630+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVUXSWOQ","created_at":"2026-07-05T09:45:56.369630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18114","citing_title":"Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10597","citing_title":"COREY: Entropy-Guided Runtime Chunk Scheduling for Selective Scan Kernels","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7","json":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7.json","graph_json":"https://pith.science/api/pith-number/WVUXSWOQ2IAZ5CBATTAA5T5HK7/graph.json","events_json":"https://pith.science/api/pith-number/WVUXSWOQ2IAZ5CBATTAA5T5HK7/events.json","paper":"https://pith.science/paper/WVUXSWOQ"},"agent_actions":{"view_html":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7","download_json":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7.json","view_paper":"https://pith.science/paper/WVUXSWOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13229&json=true","fetch_graph":"https://pith.science/api/pith-number/WVUXSWOQ2IAZ5CBATTAA5T5HK7/graph.json","fetch_events":"https://pith.science/api/pith-number/WVUXSWOQ2IAZ5CBATTAA5T5HK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7/action/storage_attestation","attest_author":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7/action/author_attestation","sign_citation":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7/action/citation_signature","submit_replication":"https://pith.science/pith/WVUXSWOQ2IAZ5CBATTAA5T5HK7/action/replication_record"}},"created_at":"2026-07-05T09:45:56.369630+00:00","updated_at":"2026-07-05T09:45:56.369630+00:00"}