{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KBJ3S4FVJRAFPABEHZWIBABJRU","short_pith_number":"pith:KBJ3S4FV","schema_version":"1.0","canonical_sha256":"5053b970b54c405780243e6c8080298d2fb1060c24e3bbf90de2221a1894bdba","source":{"kind":"arxiv","id":"2311.01927","version":2},"attestation_state":"computed","paper":{"title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DS"],"primary_cat":"cs.LG","authors_text":"Tobias Katsch","submitted_at":"2023-11-03T14:08:39Z","abstract_excerpt":"Linear Recurrence has proven to be a powerful tool for modeling long sequences efficiently. In this work, we show that existing models fail to take full advantage of its potential. Motivated by this finding, we develop GateLoop, a foundational sequence model that generalizes linear recurrent models such as S4, S5, LRU and RetNet, by employing data-controlled state transitions. Utilizing this theoretical advance, GateLoop empirically outperforms existing models for auto-regressive language modeling. Our method comes with a low-cost $O(l)$ recurrent mode and an efficient $O(l \\log_{2} l)$ parall"},"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":"2311.01927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T14:08:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DS"],"title_canon_sha256":"d1c7319fca5bf2e098b0b6b1ab2c3c489d9515582da190c498b251491e91d37e","abstract_canon_sha256":"98cdae396b95a98d68ff4d84176aeeea61ec6967d0af5a9c574e5c6aa31b1d08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:10.303702Z","signature_b64":"WuqaXnTvqVdqLeZTVmWU5pDaHo3kTn9Nh7QuMwhLQime1ImxOQmEr/6I+tHjg1Y7lGaqFsBjUGUQmT1tGTMOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5053b970b54c405780243e6c8080298d2fb1060c24e3bbf90de2221a1894bdba","last_reissued_at":"2026-07-05T07:38:10.303160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:10.303160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DS"],"primary_cat":"cs.LG","authors_text":"Tobias Katsch","submitted_at":"2023-11-03T14:08:39Z","abstract_excerpt":"Linear Recurrence has proven to be a powerful tool for modeling long sequences efficiently. In this work, we show that existing models fail to take full advantage of its potential. Motivated by this finding, we develop GateLoop, a foundational sequence model that generalizes linear recurrent models such as S4, S5, LRU and RetNet, by employing data-controlled state transitions. Utilizing this theoretical advance, GateLoop empirically outperforms existing models for auto-regressive language modeling. Our method comes with a low-cost $O(l)$ recurrent mode and an efficient $O(l \\log_{2} l)$ parall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01927","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/2311.01927/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":"2311.01927","created_at":"2026-07-05T07:38:10.303224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01927v2","created_at":"2026-07-05T07:38:10.303224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01927","created_at":"2026-07-05T07:38:10.303224+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBJ3S4FVJRAF","created_at":"2026-07-05T07:38:10.303224+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBJ3S4FVJRAFPABE","created_at":"2026-07-05T07:38:10.303224+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBJ3S4FV","created_at":"2026-07-05T07:38:10.303224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24975","citing_title":"Why Do Accumulated Transformations Extrapolate?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16533","citing_title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03825","citing_title":"Dynamic Short Convolutions Improve Transformers","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21070","citing_title":"Towards Understanding Self-Pretraining for Sequence Classification","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19427","citing_title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2312.06635","citing_title":"Gated Linear Attention Transformers with Hardware-Efficient Training","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08587","citing_title":"Kaczmarz Linear Attention","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2405.21060","citing_title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10946","citing_title":"Learning to Adapt: In-Context Learning Beyond Stationarity","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05030","citing_title":"Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU","json":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU.json","graph_json":"https://pith.science/api/pith-number/KBJ3S4FVJRAFPABEHZWIBABJRU/graph.json","events_json":"https://pith.science/api/pith-number/KBJ3S4FVJRAFPABEHZWIBABJRU/events.json","paper":"https://pith.science/paper/KBJ3S4FV"},"agent_actions":{"view_html":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU","download_json":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU.json","view_paper":"https://pith.science/paper/KBJ3S4FV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01927&json=true","fetch_graph":"https://pith.science/api/pith-number/KBJ3S4FVJRAFPABEHZWIBABJRU/graph.json","fetch_events":"https://pith.science/api/pith-number/KBJ3S4FVJRAFPABEHZWIBABJRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU/action/storage_attestation","attest_author":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU/action/author_attestation","sign_citation":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU/action/citation_signature","submit_replication":"https://pith.science/pith/KBJ3S4FVJRAFPABEHZWIBABJRU/action/replication_record"}},"created_at":"2026-07-05T07:38:10.303224+00:00","updated_at":"2026-07-05T07:38:10.303224+00:00"}