{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D7VCUP55ZO337ZIOCPQFQBMIUE","short_pith_number":"pith:D7VCUP55","schema_version":"1.0","canonical_sha256":"1fea2a3fbdcbb7bfe50e13e0580588a125c0241abf2ba7059ee3dccb7fea6a7c","source":{"kind":"arxiv","id":"2402.16819","version":2},"attestation_state":"computed","paper":{"title":"Nemotron-4 15B Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aastha Jhunjhunwala, Ameya Mahabaleshwarkar, Annika Brundyn, Ashwath Aithal, Ayush Dattagupta, Bryan Catanzaro, Chen Zhu, Dan Su, Deepak Narayanan, Denys Fridman, James Maki, Jared Casper, Jiaxuan You, Jiwei Liu, John Kamalu, Jonathan Cohen, Joseph Jennings, Jupinder Parmar, Miguel Martinez, Mohammad Shoeybi, Mostofa Patwary, Oleksii Kuchaiev, Osvald Nitski, Patrick LeGresley, Sandeep Subramanian, Shrimai Prabhumoye, Vibhu Jawa","submitted_at":"2024-02-26T18:43:45Z","abstract_excerpt":"We introduce Nemotron-4 15B, a 15-billion-parameter large multilingual language model trained on 8 trillion text tokens. Nemotron-4 15B demonstrates strong performance when assessed on English, multilingual, and coding tasks: it outperforms all existing similarly-sized open models on 4 out of 7 downstream evaluation areas and achieves competitive performance to the leading open models in the remaining ones. Specifically, Nemotron-4 15B exhibits the best multilingual capabilities of all similarly-sized models, even outperforming models over four times larger and those explicitly specialized for"},"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":"2402.16819","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:43:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d20120a05dba5ae5e1718bfda7806ad5cac3dc5c7b12e675bbf27b1765bbcd46","abstract_canon_sha256":"cc56d0cb707a712dc782aee34c77b0b1aef41ba3d5dda8e69eb1f2237b799014"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:38.037876Z","signature_b64":"kV3dy6/qtXDg4pSlGjOVA5d8+jPqICVZxI5h7tHMf+EM6kSOvSVCabRrZ1+fH0coP3nQZjJvF8dHXMuu1/oPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fea2a3fbdcbb7bfe50e13e0580588a125c0241abf2ba7059ee3dccb7fea6a7c","last_reissued_at":"2026-07-05T07:49:38.037378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:38.037378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nemotron-4 15B Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aastha Jhunjhunwala, Ameya Mahabaleshwarkar, Annika Brundyn, Ashwath Aithal, Ayush Dattagupta, Bryan Catanzaro, Chen Zhu, Dan Su, Deepak Narayanan, Denys Fridman, James Maki, Jared Casper, Jiaxuan You, Jiwei Liu, John Kamalu, Jonathan Cohen, Joseph Jennings, Jupinder Parmar, Miguel Martinez, Mohammad Shoeybi, Mostofa Patwary, Oleksii Kuchaiev, Osvald Nitski, Patrick LeGresley, Sandeep Subramanian, Shrimai Prabhumoye, Vibhu Jawa","submitted_at":"2024-02-26T18:43:45Z","abstract_excerpt":"We introduce Nemotron-4 15B, a 15-billion-parameter large multilingual language model trained on 8 trillion text tokens. Nemotron-4 15B demonstrates strong performance when assessed on English, multilingual, and coding tasks: it outperforms all existing similarly-sized open models on 4 out of 7 downstream evaluation areas and achieves competitive performance to the leading open models in the remaining ones. Specifically, Nemotron-4 15B exhibits the best multilingual capabilities of all similarly-sized models, even outperforming models over four times larger and those explicitly specialized for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16819","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/2402.16819/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":"2402.16819","created_at":"2026-07-05T07:49:38.037443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16819v2","created_at":"2026-07-05T07:49:38.037443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16819","created_at":"2026-07-05T07:49:38.037443+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7VCUP55ZO33","created_at":"2026-07-05T07:49:38.037443+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7VCUP55ZO337ZIO","created_at":"2026-07-05T07:49:38.037443+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7VCUP55","created_at":"2026-07-05T07:49:38.037443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29238","citing_title":"On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2406.07887","citing_title":"An Empirical Study of Mamba-based Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17297","citing_title":"InternLM2 Technical Report","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05365","citing_title":"ZAYA1-8B Technical Report","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01546","citing_title":"6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE","json":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE.json","graph_json":"https://pith.science/api/pith-number/D7VCUP55ZO337ZIOCPQFQBMIUE/graph.json","events_json":"https://pith.science/api/pith-number/D7VCUP55ZO337ZIOCPQFQBMIUE/events.json","paper":"https://pith.science/paper/D7VCUP55"},"agent_actions":{"view_html":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE","download_json":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE.json","view_paper":"https://pith.science/paper/D7VCUP55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16819&json=true","fetch_graph":"https://pith.science/api/pith-number/D7VCUP55ZO337ZIOCPQFQBMIUE/graph.json","fetch_events":"https://pith.science/api/pith-number/D7VCUP55ZO337ZIOCPQFQBMIUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE/action/storage_attestation","attest_author":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE/action/author_attestation","sign_citation":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE/action/citation_signature","submit_replication":"https://pith.science/pith/D7VCUP55ZO337ZIOCPQFQBMIUE/action/replication_record"}},"created_at":"2026-07-05T07:49:38.037443+00:00","updated_at":"2026-07-05T07:49:38.037443+00:00"}