{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IEGTCO6NFL4CJPY3LP4TRFNDG","short_pith_number":"pith:5IEGTCO6","schema_version":"1.0","canonical_sha256":"ea086989de6957c125f8dadfc9c4ad19918d495129100b1d985774077037978a","source":{"kind":"arxiv","id":"2402.01771","version":1},"attestation_state":"computed","paper":{"title":"BlackMamba: Mixture of Experts for State-Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Beren Millidge, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","submitted_at":"2024-02-01T07:15:58Z","abstract_excerpt":"State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently released SSM model, shows impressive performance in both language modeling and long sequence processing tasks. Simultaneously, mixture-of-expert (MoE) models have shown remarkable performance while significantly reducing the compute and latency costs of inference at the expense of a larger memory footprint. In this paper, we present BlackMamba, a novel archit"},"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":"2402.01771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T07:15:58Z","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"title_canon_sha256":"99fc5c4d3c8ac788467bff3d60ebcf326b167795cde10e27cddf69eaf378287f","abstract_canon_sha256":"26a3a2686c199c34f006f651ade6e5c4567bc3cca4add05300684d11f011e82f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:06.582118Z","signature_b64":"8oyxo62qiGItMsbQwiP2WEGgySL23kGBNuTRntsrMRwOrG7Mu1bgyaXXr9QO59A9U1Pvq9bQ6W0pXcIsrcDKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea086989de6957c125f8dadfc9c4ad19918d495129100b1d985774077037978a","last_reissued_at":"2026-07-05T07:41:06.581616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:06.581616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlackMamba: Mixture of Experts for State-Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Beren Millidge, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","submitted_at":"2024-02-01T07:15:58Z","abstract_excerpt":"State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently released SSM model, shows impressive performance in both language modeling and long sequence processing tasks. Simultaneously, mixture-of-expert (MoE) models have shown remarkable performance while significantly reducing the compute and latency costs of inference at the expense of a larger memory footprint. In this paper, we present BlackMamba, a novel archit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01771","kind":"arxiv","version":1},"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/2402.01771/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":"2402.01771","created_at":"2026-07-05T07:41:06.581680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01771v1","created_at":"2026-07-05T07:41:06.581680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01771","created_at":"2026-07-05T07:41:06.581680+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IEGTCO6NFL4","created_at":"2026-07-05T07:41:06.581680+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IEGTCO6NFL4CJPY","created_at":"2026-07-05T07:41:06.581680+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IEGTCO6","created_at":"2026-07-05T07:41:06.581680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21868","citing_title":"WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10395","citing_title":"Efficient RWKV-based Representation Learning for 3D Point Clouds","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01972","citing_title":"Hidden State Poisoning Attacks against Mamba-based Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05365","citing_title":"ZAYA1-8B Technical Report","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG","json":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG.json","graph_json":"https://pith.science/api/pith-number/5IEGTCO6NFL4CJPY3LP4TRFNDG/graph.json","events_json":"https://pith.science/api/pith-number/5IEGTCO6NFL4CJPY3LP4TRFNDG/events.json","paper":"https://pith.science/paper/5IEGTCO6"},"agent_actions":{"view_html":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG","download_json":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG.json","view_paper":"https://pith.science/paper/5IEGTCO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01771&json=true","fetch_graph":"https://pith.science/api/pith-number/5IEGTCO6NFL4CJPY3LP4TRFNDG/graph.json","fetch_events":"https://pith.science/api/pith-number/5IEGTCO6NFL4CJPY3LP4TRFNDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG/action/storage_attestation","attest_author":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG/action/author_attestation","sign_citation":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG/action/citation_signature","submit_replication":"https://pith.science/pith/5IEGTCO6NFL4CJPY3LP4TRFNDG/action/replication_record"}},"created_at":"2026-07-05T07:41:06.581680+00:00","updated_at":"2026-07-05T07:41:06.581680+00:00"}