{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QB7JTKLQVS4Q3GJREWPISCWHX6","short_pith_number":"pith:QB7JTKLQ","schema_version":"1.0","canonical_sha256":"807e99a970acb90d9931259e890ac7bf8621c2eb7f54dc37d457809a1b01431d","source":{"kind":"arxiv","id":"2410.05355","version":1},"attestation_state":"computed","paper":{"title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhia Eddine Rhaiem, Guillaume Kunsch, Hakim Hacid, Ilyas Chahed, Jingwei Zuo, Maksim Velikanov, Younes Belkada","submitted_at":"2024-10-07T15:40:45Z","abstract_excerpt":"In this technical report, we present Falcon Mamba 7B, a new base large language model based on the novel Mamba architecture. Falcon Mamba 7B is trained on 5.8 trillion tokens with carefully selected data mixtures. As a pure Mamba-based model, Falcon Mamba 7B surpasses leading open-weight models based on Transformers, such as Mistral 7B, Llama3.1 8B, and Falcon2 11B. It is on par with Gemma 7B and outperforms models with different architecture designs, such as RecurrentGemma 9B and RWKV-v6 Finch 7B/14B. Currently, Falcon Mamba 7B is the best-performing Mamba model in the literature at this scal"},"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":"2410.05355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T15:40:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7cf558c870856f664db7a7c6f0a1f2560497b03def9cf48bdbef6f2ce4d2962e","abstract_canon_sha256":"7c3dcc24bbb0ea35a9e4f4739260c4d4f26137670dd5aa3eb15488e56ff0cea6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:18.063212Z","signature_b64":"3eW2IhDdPs0U1u17tco40E65ZKIq/9ShYd7B7HLXJxJurB46I4V42FoXixvtlxswlRb3+zJYewekj3b/idCyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"807e99a970acb90d9931259e890ac7bf8621c2eb7f54dc37d457809a1b01431d","last_reissued_at":"2026-07-05T09:17:18.062727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:18.062727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhia Eddine Rhaiem, Guillaume Kunsch, Hakim Hacid, Ilyas Chahed, Jingwei Zuo, Maksim Velikanov, Younes Belkada","submitted_at":"2024-10-07T15:40:45Z","abstract_excerpt":"In this technical report, we present Falcon Mamba 7B, a new base large language model based on the novel Mamba architecture. Falcon Mamba 7B is trained on 5.8 trillion tokens with carefully selected data mixtures. As a pure Mamba-based model, Falcon Mamba 7B surpasses leading open-weight models based on Transformers, such as Mistral 7B, Llama3.1 8B, and Falcon2 11B. It is on par with Gemma 7B and outperforms models with different architecture designs, such as RecurrentGemma 9B and RWKV-v6 Finch 7B/14B. Currently, Falcon Mamba 7B is the best-performing Mamba model in the literature at this scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05355","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/2410.05355/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":"2410.05355","created_at":"2026-07-05T09:17:18.062786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05355v1","created_at":"2026-07-05T09:17:18.062786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05355","created_at":"2026-07-05T09:17:18.062786+00:00"},{"alias_kind":"pith_short_12","alias_value":"QB7JTKLQVS4Q","created_at":"2026-07-05T09:17:18.062786+00:00"},{"alias_kind":"pith_short_16","alias_value":"QB7JTKLQVS4Q3GJR","created_at":"2026-07-05T09:17:18.062786+00:00"},{"alias_kind":"pith_short_8","alias_value":"QB7JTKLQ","created_at":"2026-07-05T09:17:18.062786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08399","citing_title":"Prompt Compression via Activation Aggregation","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22917","citing_title":"GRAIN: Group Aggregation via Min-Norm Objective","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20295","citing_title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06315","citing_title":"LLM Self-Recognition: Steering and Retrieving Activation Signatures","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24025","citing_title":"Towards Large Model Feature Coding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29904","citing_title":"Timesteps of Mamba Align with Human Reading Times","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2412.15176","citing_title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05276","citing_title":"SpikingBrain: Spiking Brain-inspired Large Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03829","citing_title":"Mambalaya: Einsum-Based Fusion Optimizations on State-Space Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06129","citing_title":"PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6","json":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6.json","graph_json":"https://pith.science/api/pith-number/QB7JTKLQVS4Q3GJREWPISCWHX6/graph.json","events_json":"https://pith.science/api/pith-number/QB7JTKLQVS4Q3GJREWPISCWHX6/events.json","paper":"https://pith.science/paper/QB7JTKLQ"},"agent_actions":{"view_html":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6","download_json":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6.json","view_paper":"https://pith.science/paper/QB7JTKLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05355&json=true","fetch_graph":"https://pith.science/api/pith-number/QB7JTKLQVS4Q3GJREWPISCWHX6/graph.json","fetch_events":"https://pith.science/api/pith-number/QB7JTKLQVS4Q3GJREWPISCWHX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6/action/storage_attestation","attest_author":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6/action/author_attestation","sign_citation":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6/action/citation_signature","submit_replication":"https://pith.science/pith/QB7JTKLQVS4Q3GJREWPISCWHX6/action/replication_record"}},"created_at":"2026-07-05T09:17:18.062786+00:00","updated_at":"2026-07-05T09:17:18.062786+00:00"}