{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KCS3SF7RYH2DEOOSX55HL7UX6E","short_pith_number":"pith:KCS3SF7R","schema_version":"1.0","canonical_sha256":"50a5b917f1c1f43239d2bf7a75fe97f1031bdecf1b5818c8cea1f360fbcd1a76","source":{"kind":"arxiv","id":"2411.01663","version":1},"attestation_state":"computed","paper":{"title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Majid Daliri, Zhao Song","submitted_at":"2024-11-03T19:18:57Z","abstract_excerpt":"Recently, 1-bit Large Language Models (LLMs) have emerged, showcasing an impressive combination of efficiency and performance that rivals traditional LLMs. Research by Wang et al. (2023); Ma et al. (2024) indicates that the performance of these 1-bit LLMs progressively improves as the number of parameters increases, hinting at the potential existence of a Scaling Law for 1-bit Neural Networks. In this paper, we present the first theoretical result that rigorously establishes this scaling law for 1-bit models. We prove that, despite the constraint of weights restricted to $\\{-1, +1\\}$, the dyna"},"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":"2411.01663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T19:18:57Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CL"],"title_canon_sha256":"a9c428988c3128fd2954807358e1c967ecdbe4827255c4a8b1b355b65a99b7d4","abstract_canon_sha256":"334460ee9e394f2eeb940fe56a86e9c81b26697bb256e6455fd0d870c36edb54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:34.183334Z","signature_b64":"tWHkeQlspXGd/EudLzUVDNG/1PmlTvHduCKCkzluPeV4MJsFaP1HdQQYjgx5cYoXMmKAs8SuFJIokaot3qxYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50a5b917f1c1f43239d2bf7a75fe97f1031bdecf1b5818c8cea1f360fbcd1a76","last_reissued_at":"2026-07-05T09:30:34.182851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:34.182851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Majid Daliri, Zhao Song","submitted_at":"2024-11-03T19:18:57Z","abstract_excerpt":"Recently, 1-bit Large Language Models (LLMs) have emerged, showcasing an impressive combination of efficiency and performance that rivals traditional LLMs. Research by Wang et al. (2023); Ma et al. (2024) indicates that the performance of these 1-bit LLMs progressively improves as the number of parameters increases, hinting at the potential existence of a Scaling Law for 1-bit Neural Networks. In this paper, we present the first theoretical result that rigorously establishes this scaling law for 1-bit models. We prove that, despite the constraint of weights restricted to $\\{-1, +1\\}$, the dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01663","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/2411.01663/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":"2411.01663","created_at":"2026-07-05T09:30:34.182909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01663v1","created_at":"2026-07-05T09:30:34.182909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01663","created_at":"2026-07-05T09:30:34.182909+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCS3SF7RYH2D","created_at":"2026-07-05T09:30:34.182909+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCS3SF7RYH2DEOOS","created_at":"2026-07-05T09:30:34.182909+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCS3SF7R","created_at":"2026-07-05T09:30:34.182909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E","json":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E.json","graph_json":"https://pith.science/api/pith-number/KCS3SF7RYH2DEOOSX55HL7UX6E/graph.json","events_json":"https://pith.science/api/pith-number/KCS3SF7RYH2DEOOSX55HL7UX6E/events.json","paper":"https://pith.science/paper/KCS3SF7R"},"agent_actions":{"view_html":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E","download_json":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E.json","view_paper":"https://pith.science/paper/KCS3SF7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01663&json=true","fetch_graph":"https://pith.science/api/pith-number/KCS3SF7RYH2DEOOSX55HL7UX6E/graph.json","fetch_events":"https://pith.science/api/pith-number/KCS3SF7RYH2DEOOSX55HL7UX6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E/action/storage_attestation","attest_author":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E/action/author_attestation","sign_citation":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E/action/citation_signature","submit_replication":"https://pith.science/pith/KCS3SF7RYH2DEOOSX55HL7UX6E/action/replication_record"}},"created_at":"2026-07-05T09:30:34.182909+00:00","updated_at":"2026-07-05T09:30:34.182909+00:00"}