{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3UBC6H7BDA5ZDIKYAOCN7OVGI2","short_pith_number":"pith:3UBC6H7B","schema_version":"1.0","canonical_sha256":"dd022f1fe1183b91a1580384dfbaa646b2a089e95f9ccf0b675287b10866f960","source":{"kind":"arxiv","id":"2412.01152","version":1},"attestation_state":"computed","paper":{"title":"INTELLECT-1 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Charles Goddard, Elie Bakouch, Fares Obeid, Jack Min Ong, Jannik Straube, Johannes Hagemann, Lucas Atkins, Manveer Basra, Max Ryabinin, Maziyar Panahi, Michael Keiblinger, Sami Jaghouar","submitted_at":"2024-12-02T05:52:32Z","abstract_excerpt":"In this report, we introduce INTELLECT-1, the first 10 billion parameter language model collaboratively trained across the globe, demonstrating that large-scale model training is no longer confined to large corporations but can be achieved through a distributed, community-driven approach. INTELLECT-1 was trained on 1 trillion tokens using up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent compute providers dynamically joining and leaving the training process, while maintaining 83-96% compute utilization and 36.2-41.4% model FLOPS utilization. We l"},"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":"2412.01152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-02T05:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"15b5724ef95bad42fd5e04d9ebe47f82dbf8edf5a9e2a00302f79808f445e65e","abstract_canon_sha256":"9c6c4650011e425cb1be9bf6067e961a3cec34031aff7c3957169be1b8ac800d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:54.857176Z","signature_b64":"hi4ziaQI8XMWk+mG7rT4Kjxo7Z6+DcvXmYpP/beBqDrOiyWbwPwavnyXGzx4kT74GF54SwcL4UmgcK3EkGTeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd022f1fe1183b91a1580384dfbaa646b2a089e95f9ccf0b675287b10866f960","last_reissued_at":"2026-07-05T09:42:54.856656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:54.856656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INTELLECT-1 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Charles Goddard, Elie Bakouch, Fares Obeid, Jack Min Ong, Jannik Straube, Johannes Hagemann, Lucas Atkins, Manveer Basra, Max Ryabinin, Maziyar Panahi, Michael Keiblinger, Sami Jaghouar","submitted_at":"2024-12-02T05:52:32Z","abstract_excerpt":"In this report, we introduce INTELLECT-1, the first 10 billion parameter language model collaboratively trained across the globe, demonstrating that large-scale model training is no longer confined to large corporations but can be achieved through a distributed, community-driven approach. INTELLECT-1 was trained on 1 trillion tokens using up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent compute providers dynamically joining and leaving the training process, while maintaining 83-96% compute utilization and 36.2-41.4% model FLOPS utilization. We l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01152","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/2412.01152/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":"2412.01152","created_at":"2026-07-05T09:42:54.856735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01152v1","created_at":"2026-07-05T09:42:54.856735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01152","created_at":"2026-07-05T09:42:54.856735+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UBC6H7BDA5Z","created_at":"2026-07-05T09:42:54.856735+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UBC6H7BDA5ZDIKY","created_at":"2026-07-05T09:42:54.856735+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UBC6H7B","created_at":"2026-07-05T09:42:54.856735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24722","citing_title":"Decentralised AI Training and Inference with BlockTrain","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12273","citing_title":"Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00208","citing_title":"SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01128","citing_title":"Local MixVR: Breaking the Communication-Sample Dependence in Distributed Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06542","citing_title":"On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2","json":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2.json","graph_json":"https://pith.science/api/pith-number/3UBC6H7BDA5ZDIKYAOCN7OVGI2/graph.json","events_json":"https://pith.science/api/pith-number/3UBC6H7BDA5ZDIKYAOCN7OVGI2/events.json","paper":"https://pith.science/paper/3UBC6H7B"},"agent_actions":{"view_html":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2","download_json":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2.json","view_paper":"https://pith.science/paper/3UBC6H7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01152&json=true","fetch_graph":"https://pith.science/api/pith-number/3UBC6H7BDA5ZDIKYAOCN7OVGI2/graph.json","fetch_events":"https://pith.science/api/pith-number/3UBC6H7BDA5ZDIKYAOCN7OVGI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2/action/storage_attestation","attest_author":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2/action/author_attestation","sign_citation":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2/action/citation_signature","submit_replication":"https://pith.science/pith/3UBC6H7BDA5ZDIKYAOCN7OVGI2/action/replication_record"}},"created_at":"2026-07-05T09:42:54.856735+00:00","updated_at":"2026-07-05T09:42:54.856735+00:00"}