{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:23ZEPV2YBMQQWAXTUCS4GTVTML","short_pith_number":"pith:23ZEPV2Y","schema_version":"1.0","canonical_sha256":"d6f247d7580b210b02f3a0a5c34eb362e434871a361617d108dca7ace156604d","source":{"kind":"arxiv","id":"2601.21766","version":4},"attestation_state":"computed","paper":{"title":"CoFrGeNet: Continued Fraction Architectures for Language Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Continued-fraction components replace attention and feed-forward layers in large transformers with half to two-thirds the parameters while matching or exceeding performance on language tasks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amit Dhurandhar, Dennis Wei, Karthikeyan Natesan Ramamurthy, Rahul Nair, Tejaswini Pedapati, Vijil Chenthamarakshan","submitted_at":"2026-01-29T14:16:39Z","abstract_excerpt":"Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function class is named CoFrGeNets - Continued Fraction Generative Networks. We design novel architectural components based on this function class that can replace Multi-head Attention and Feed-Forward Networks in Transformer blocks while requiring much fewer parameters. We derive custom gradient formulations to optimize the proposed components more accurately and effici"},"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":true},"canonical_record":{"source":{"id":"2601.21766","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T14:16:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3fb0b68e932ede11292cdb8cf8460f267c04394665d0887589e98bfb3aef976","abstract_canon_sha256":"cd8be869b46ce6ae8e1dc41fa4026452bb7fb98020eba61eb7978cd0b08053fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:12.893275Z","signature_b64":"gPIKbDDxr9tdY0gyCCsZ7BqpUfnvZQGoBBDrmqzpEnrENbFshrP65/ASBqRaPA9oA18VE3X9THBGUo/6adwdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6f247d7580b210b02f3a0a5c34eb362e434871a361617d108dca7ace156604d","last_reissued_at":"2026-05-25T02:02:12.892377Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:12.892377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoFrGeNet: Continued Fraction Architectures for Language Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Continued-fraction components replace attention and feed-forward layers in large transformers with half to two-thirds the parameters while matching or exceeding performance on language tasks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amit Dhurandhar, Dennis Wei, Karthikeyan Natesan Ramamurthy, Rahul Nair, Tejaswini Pedapati, Vijil Chenthamarakshan","submitted_at":"2026-01-29T14:16:39Z","abstract_excerpt":"Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function class is named CoFrGeNets - Continued Fraction Generative Networks. We design novel architectural components based on this function class that can replace Multi-head Attention and Feed-Forward Networks in Transformer blocks while requiring much fewer parameters. We derive custom gradient formulations to optimize the proposed components more accurately and effici"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show that the performance on downstream classification, Q&A, reasoning and text understanding tasks of our models is competitive and sometimes even superior to the original models with 2/3 to 1/2 the parameters and shorter pre-training time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That continued-fraction components can preserve the modeling capacity of attention and feed-forward layers while using far fewer parameters, and that the custom gradient rules produce stable optimization across large-scale pre-training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoFrGeNet uses continued-fraction function classes to build transformer replacements that match or beat GPT-2 and Llama performance with half to two-thirds the parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Continued-fraction components replace attention and feed-forward layers in large transformers with half to two-thirds the parameters while matching or exceeding performance on language tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1c791f7da8a642bb60dac7de2216135f80bbd98b8f66719bcea55c9252a80468"},"source":{"id":"2601.21766","kind":"arxiv","version":4},"verdict":{"id":"e3309cf7-b466-427e-a6fb-ccdbd310817e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:43:55.537445Z","strongest_claim":"Results show that the performance on downstream classification, Q&A, reasoning and text understanding tasks of our models is competitive and sometimes even superior to the original models with 2/3 to 1/2 the parameters and shorter pre-training time.","one_line_summary":"CoFrGeNet uses continued-fraction function classes to build transformer replacements that match or beat GPT-2 and Llama performance with half to two-thirds the parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That continued-fraction components can preserve the modeling capacity of attention and feed-forward layers while using far fewer parameters, and that the custom gradient rules produce stable optimization across large-scale pre-training.","pith_extraction_headline":"Continued-fraction components replace attention and feed-forward layers in large transformers with half to two-thirds the parameters while matching or exceeding performance on language tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.21766/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":2,"snapshot_sha256":"1420dd19caee143aa61b19d2163d453763b9c16796eb0c9ef10f94c342f5ee1c"},"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":"2601.21766","created_at":"2026-05-25T02:02:12.892494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21766v4","created_at":"2026-05-25T02:02:12.892494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21766","created_at":"2026-05-25T02:02:12.892494+00:00"},{"alias_kind":"pith_short_12","alias_value":"23ZEPV2YBMQQ","created_at":"2026-05-25T02:02:12.892494+00:00"},{"alias_kind":"pith_short_16","alias_value":"23ZEPV2YBMQQWAXT","created_at":"2026-05-25T02:02:12.892494+00:00"},{"alias_kind":"pith_short_8","alias_value":"23ZEPV2Y","created_at":"2026-05-25T02:02:12.892494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML","json":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML.json","graph_json":"https://pith.science/api/pith-number/23ZEPV2YBMQQWAXTUCS4GTVTML/graph.json","events_json":"https://pith.science/api/pith-number/23ZEPV2YBMQQWAXTUCS4GTVTML/events.json","paper":"https://pith.science/paper/23ZEPV2Y"},"agent_actions":{"view_html":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML","download_json":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML.json","view_paper":"https://pith.science/paper/23ZEPV2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21766&json=true","fetch_graph":"https://pith.science/api/pith-number/23ZEPV2YBMQQWAXTUCS4GTVTML/graph.json","fetch_events":"https://pith.science/api/pith-number/23ZEPV2YBMQQWAXTUCS4GTVTML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML/action/storage_attestation","attest_author":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML/action/author_attestation","sign_citation":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML/action/citation_signature","submit_replication":"https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML/action/replication_record"}},"created_at":"2026-05-25T02:02:12.892494+00:00","updated_at":"2026-05-25T02:02:12.892494+00:00"}