{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CNSLE5XFFGKERHSWK5ZO6UY5V","short_pith_number":"pith:5CNSLE5X","schema_version":"1.0","canonical_sha256":"e89b2593b7294ca244f2b2bb977a98ed53e67ccd01a375d0f341d1d965416692","source":{"kind":"arxiv","id":"2406.16690","version":1},"attestation_state":"computed","paper":{"title":"Scaling Laws for Linear Complexity Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Li, Ruitao Leng, Weigao Sun, Xuyang Shen, Yiran Zhong, Zhen Qin","submitted_at":"2024-06-24T14:51:31Z","abstract_excerpt":"The interest in linear complexity models for large language models is on the rise, although their scaling capacity remains uncertain. In this study, we present the scaling laws for linear complexity language models to establish a foundation for their scalability. Specifically, we examine the scaling behaviors of three efficient linear architectures. These include TNL, a linear attention model with data-independent decay; HGRN2, a linear RNN with data-dependent decay; and cosFormer2, a linear attention model without decay. We also include LLaMA as a baseline architecture for softmax attention f"},"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":"2406.16690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:51:31Z","cross_cats_sorted":[],"title_canon_sha256":"ec773ddff4450050fa165f54e22c3668f0a1c447764f034fe2a260fb2c44940b","abstract_canon_sha256":"2ea6e2c0fef94166b4fe7360176dec1ba4eb74cd5cafc30da5bbc622fecfcf45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:02.253036Z","signature_b64":"A/FhCO5R8tfAnI6tr1x25S0tKVYD0+O1hy8vIO7vqpz72+SHD+iBxu7NCyG0MmCZTmz9WfOBRjl43CaR511kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e89b2593b7294ca244f2b2bb977a98ed53e67ccd01a375d0f341d1d965416692","last_reissued_at":"2026-07-05T08:36:02.252544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:02.252544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws for Linear Complexity Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Li, Ruitao Leng, Weigao Sun, Xuyang Shen, Yiran Zhong, Zhen Qin","submitted_at":"2024-06-24T14:51:31Z","abstract_excerpt":"The interest in linear complexity models for large language models is on the rise, although their scaling capacity remains uncertain. In this study, we present the scaling laws for linear complexity language models to establish a foundation for their scalability. Specifically, we examine the scaling behaviors of three efficient linear architectures. These include TNL, a linear attention model with data-independent decay; HGRN2, a linear RNN with data-dependent decay; and cosFormer2, a linear attention model without decay. We also include LLaMA as a baseline architecture for softmax attention f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16690","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/2406.16690/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":"2406.16690","created_at":"2026-07-05T08:36:02.252603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16690v1","created_at":"2026-07-05T08:36:02.252603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16690","created_at":"2026-07-05T08:36:02.252603+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CNSLE5XFFGK","created_at":"2026-07-05T08:36:02.252603+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CNSLE5XFFGKERHS","created_at":"2026-07-05T08:36:02.252603+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CNSLE5X","created_at":"2026-07-05T08:36:02.252603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26248","citing_title":"Unified Neural Scaling Laws","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V","json":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V.json","graph_json":"https://pith.science/api/pith-number/5CNSLE5XFFGKERHSWK5ZO6UY5V/graph.json","events_json":"https://pith.science/api/pith-number/5CNSLE5XFFGKERHSWK5ZO6UY5V/events.json","paper":"https://pith.science/paper/5CNSLE5X"},"agent_actions":{"view_html":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V","download_json":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V.json","view_paper":"https://pith.science/paper/5CNSLE5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16690&json=true","fetch_graph":"https://pith.science/api/pith-number/5CNSLE5XFFGKERHSWK5ZO6UY5V/graph.json","fetch_events":"https://pith.science/api/pith-number/5CNSLE5XFFGKERHSWK5ZO6UY5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V/action/storage_attestation","attest_author":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V/action/author_attestation","sign_citation":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V/action/citation_signature","submit_replication":"https://pith.science/pith/5CNSLE5XFFGKERHSWK5ZO6UY5V/action/replication_record"}},"created_at":"2026-07-05T08:36:02.252603+00:00","updated_at":"2026-07-05T08:36:02.252603+00:00"}