{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5IEGTCO6NFL4CJPY3LP4TRFNDG","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":"26a3a2686c199c34f006f651ade6e5c4567bc3cca4add05300684d11f011e82f","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T07:15:58Z","title_canon_sha256":"99fc5c4d3c8ac788467bff3d60ebcf326b167795cde10e27cddf69eaf378287f"},"schema_version":"1.0","source":{"id":"2402.01771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01771","created_at":"2026-07-05T07:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01771v1","created_at":"2026-07-05T07:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01771","created_at":"2026-07-05T07:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"5IEGTCO6NFL4","created_at":"2026-07-05T07:41:06Z"},{"alias_kind":"pith_short_16","alias_value":"5IEGTCO6NFL4CJPY","created_at":"2026-07-05T07:41:06Z"},{"alias_kind":"pith_short_8","alias_value":"5IEGTCO6","created_at":"2026-07-05T07:41:06Z"}],"graph_snapshots":[{"event_id":"sha256:f58a0839ec4279850e791dca13c234ceb420ed4df5d2462a1cdd654f66e01830","target":"graph","created_at":"2026-07-05T07:41:06Z","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/2402.01771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Beren Millidge, Paolo Glorioso, Quentin Anthony, Yury Tokpanov","cross_cats":["cs.AI","cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T07:15:58Z","title":"BlackMamba: Mixture of Experts for State-Space Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01771","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":"sha256:76b0993bb6de8de21aaea813fd3ab6f03f5fd8cfb01593a9c83dafa908a93fcf","target":"record","created_at":"2026-07-05T07:41:06Z","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":"26a3a2686c199c34f006f651ade6e5c4567bc3cca4add05300684d11f011e82f","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T07:15:58Z","title_canon_sha256":"99fc5c4d3c8ac788467bff3d60ebcf326b167795cde10e27cddf69eaf378287f"},"schema_version":"1.0","source":{"id":"2402.01771","kind":"arxiv","version":1}},"canonical_sha256":"ea086989de6957c125f8dadfc9c4ad19918d495129100b1d985774077037978a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea086989de6957c125f8dadfc9c4ad19918d495129100b1d985774077037978a","first_computed_at":"2026-07-05T07:41:06.581616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:06.581616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8oyxo62qiGItMsbQwiP2WEGgySL23kGBNuTRntsrMRwOrG7Mu1bgyaXXr9QO59A9U1Pvq9bQ6W0pXcIsrcDKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:06.582118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76b0993bb6de8de21aaea813fd3ab6f03f5fd8cfb01593a9c83dafa908a93fcf","sha256:f58a0839ec4279850e791dca13c234ceb420ed4df5d2462a1cdd654f66e01830"],"state_sha256":"86a56a6fa69911aea4d19622dcf928286a6c0565216cd50fbf65a79d55d86a38"}