{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MRLI72XKPNEHZLBBCLOP7UHJJL","short_pith_number":"pith:MRLI72XK","canonical_record":{"source":{"id":"2401.04081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T18:35:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dade418c5d8c36318f54866fbb4ef004ed02d988699e93352c20ada915178f7f","abstract_canon_sha256":"cd2157d5fc00ed8a8a2216d8d0018a0243d31901148cce02fbc86caf5976f8c9"},"schema_version":"1.0"},"canonical_sha256":"64568feaea7b487cac2112dcffd0e94af631ed27c3085124271fd65ba4431259","source":{"kind":"arxiv","id":"2401.04081","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04081","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04081v2","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04081","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"MRLI72XKPNEH","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_16","alias_value":"MRLI72XKPNEHZLBB","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_8","alias_value":"MRLI72XK","created_at":"2026-07-05T07:49:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MRLI72XKPNEHZLBBCLOP7UHJJL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.04081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T18:35:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dade418c5d8c36318f54866fbb4ef004ed02d988699e93352c20ada915178f7f","abstract_canon_sha256":"cd2157d5fc00ed8a8a2216d8d0018a0243d31901148cce02fbc86caf5976f8c9"},"schema_version":"1.0"},"canonical_sha256":"64568feaea7b487cac2112dcffd0e94af631ed27c3085124271fd65ba4431259","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:17.173204Z","signature_b64":"nfnrJHP3RdWZad+jXXS4lRJ9CnKFfLKftyXQVfVYuf4qco8u1etmJPHBu+uUGGPX6IN8dcZ0n+yynGnk//CaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64568feaea7b487cac2112dcffd0e94af631ed27c3085124271fd65ba4431259","last_reissued_at":"2026-07-05T07:49:17.172720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:17.172720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.04081","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqlW1NNczOSDJzVQFfU62Qwpm68RfJUMhPLWVKFGakjGMX4hRQktHJNxTTlecIU9eYJRGag0Pl7qOns2fIujAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:54:44.929044Z"},"content_sha256":"5fd7a55eebec0075b928d234d0d6a1fda61a9d4c0f6939acede21851a3f4ca13","schema_version":"1.0","event_id":"sha256:5fd7a55eebec0075b928d234d0d6a1fda61a9d4c0f6939acede21851a3f4ca13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MRLI72XKPNEHZLBBCLOP7UHJJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Kr\\'ol, Maciej Pi\\'oro, Marek Cygan, Micha{\\l} Krutul, Piotr Mi{\\l}o\\'s, Sebastian Jaszczur, Szymon Antoniak","submitted_at":"2024-01-08T18:35:07Z","abstract_excerpt":"State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE. We showcase this on Mamba, a recent SSM-based model that achieves remarkable performance. Our model, MoE-Mamba, outperforms both Mamba and baseline Transformer-MoE. In particular, MoE-Mamba reaches the same per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04081","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/2401.04081/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vswH9pDDLFjnpEdm3mi9TMzfRpmzTFEjQvf9U9FIKQPsbW+RtgwQ/1v3CeX8FT/82sAQ8kwkfTEsedVnoejgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:54:44.929444Z"},"content_sha256":"5eb9c66a2b14f75015ca1732fe12fe5b1864ebd7e4d2f183c2ac4934d1e21a24","schema_version":"1.0","event_id":"sha256:5eb9c66a2b14f75015ca1732fe12fe5b1864ebd7e4d2f183c2ac4934d1e21a24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/bundle.json","state_url":"https://pith.science/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:54:44Z","links":{"resolver":"https://pith.science/pith/MRLI72XKPNEHZLBBCLOP7UHJJL","bundle":"https://pith.science/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/bundle.json","state":"https://pith.science/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRLI72XKPNEHZLBBCLOP7UHJJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MRLI72XKPNEHZLBBCLOP7UHJJL","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":"cd2157d5fc00ed8a8a2216d8d0018a0243d31901148cce02fbc86caf5976f8c9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T18:35:07Z","title_canon_sha256":"dade418c5d8c36318f54866fbb4ef004ed02d988699e93352c20ada915178f7f"},"schema_version":"1.0","source":{"id":"2401.04081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04081","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04081v2","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04081","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"MRLI72XKPNEH","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_16","alias_value":"MRLI72XKPNEHZLBB","created_at":"2026-07-05T07:49:17Z"},{"alias_kind":"pith_short_8","alias_value":"MRLI72XK","created_at":"2026-07-05T07:49:17Z"}],"graph_snapshots":[{"event_id":"sha256:5eb9c66a2b14f75015ca1732fe12fe5b1864ebd7e4d2f183c2ac4934d1e21a24","target":"graph","created_at":"2026-07-05T07:49:17Z","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/2401.04081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE. We showcase this on Mamba, a recent SSM-based model that achieves remarkable performance. Our model, MoE-Mamba, outperforms both Mamba and baseline Transformer-MoE. In particular, MoE-Mamba reaches the same per","authors_text":"Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Kr\\'ol, Maciej Pi\\'oro, Marek Cygan, Micha{\\l} Krutul, Piotr Mi{\\l}o\\'s, Sebastian Jaszczur, Szymon Antoniak","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T18:35:07Z","title":"MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04081","kind":"arxiv","version":2},"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":"sha256:5fd7a55eebec0075b928d234d0d6a1fda61a9d4c0f6939acede21851a3f4ca13","target":"record","created_at":"2026-07-05T07:49:17Z","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":"cd2157d5fc00ed8a8a2216d8d0018a0243d31901148cce02fbc86caf5976f8c9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T18:35:07Z","title_canon_sha256":"dade418c5d8c36318f54866fbb4ef004ed02d988699e93352c20ada915178f7f"},"schema_version":"1.0","source":{"id":"2401.04081","kind":"arxiv","version":2}},"canonical_sha256":"64568feaea7b487cac2112dcffd0e94af631ed27c3085124271fd65ba4431259","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64568feaea7b487cac2112dcffd0e94af631ed27c3085124271fd65ba4431259","first_computed_at":"2026-07-05T07:49:17.172720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:17.172720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nfnrJHP3RdWZad+jXXS4lRJ9CnKFfLKftyXQVfVYuf4qco8u1etmJPHBu+uUGGPX6IN8dcZ0n+yynGnk//CaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:17.173204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fd7a55eebec0075b928d234d0d6a1fda61a9d4c0f6939acede21851a3f4ca13","sha256:5eb9c66a2b14f75015ca1732fe12fe5b1864ebd7e4d2f183c2ac4934d1e21a24"],"state_sha256":"4d630cc0ee5e24576f50c22c8eaa6cafc8cd0988d9aae783dfb54bf0ea6a11f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPjWJvK/xCk0RPotYeHrdXQ6XX0eboKHiXJOoT7i+N88zB8eJ/En4nm42s/7+j88dj8cTVqAE05x3E1nI8riCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:54:44.931490Z","bundle_sha256":"74cbf327a1ff4a5ba75ce51cafc259c17e70857daa271d8eea2815340d17507f"}}