{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T7SWU3XHZ3UBVUNTCP4KAMT7HY","short_pith_number":"pith:T7SWU3XH","schema_version":"1.0","canonical_sha256":"9fe56a6ee7cee81ad1b313f8a0327f3e14c2dfbd98cb2588b4c19493d00c8f65","source":{"kind":"arxiv","id":"2501.02573","version":1},"attestation_state":"computed","paper":{"title":"LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MS"],"primary_cat":"cs.LG","authors_text":"Jiaping Wang, Qiao-Chu He, Simiao Zhang, Yifan Chen","submitted_at":"2025-01-05T15:11:26Z","abstract_excerpt":"The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal attention in a generative pre-trained transformer (GPT) with \\emph{exponentially decaying causal linear attention}. In this paper, we present LeetDecoding, which is the first Python package that provides a large set of computation routines for this fundamental operator. The launch of LeetDecoding was motivated by the current lack of (1) clear understanding of the complexity reg"},"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":"2501.02573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-05T15:11:26Z","cross_cats_sorted":["cs.CL","cs.MS"],"title_canon_sha256":"6c5b7cbc6a80959f571b6f03e0a9b81a0dba9990eebd068433f7ea83aaf47ac5","abstract_canon_sha256":"c825f63d01249a3d8209a5077924e39e3e99a7954651f1d90edb0e60ac48057b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:09.293279Z","signature_b64":"YuGLazw8+KN6pENX6Wl62kYstA16yF7hHM93eQSRG+2xYvtjf3j9YWv9UezeMhcipJN98G6VG9UX9gOCVOb3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fe56a6ee7cee81ad1b313f8a0327f3e14c2dfbd98cb2588b4c19493d00c8f65","last_reissued_at":"2026-07-05T09:57:09.292851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:09.292851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MS"],"primary_cat":"cs.LG","authors_text":"Jiaping Wang, Qiao-Chu He, Simiao Zhang, Yifan Chen","submitted_at":"2025-01-05T15:11:26Z","abstract_excerpt":"The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal attention in a generative pre-trained transformer (GPT) with \\emph{exponentially decaying causal linear attention}. In this paper, we present LeetDecoding, which is the first Python package that provides a large set of computation routines for this fundamental operator. The launch of LeetDecoding was motivated by the current lack of (1) clear understanding of the complexity reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02573","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/2501.02573/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":"2501.02573","created_at":"2026-07-05T09:57:09.292906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02573v1","created_at":"2026-07-05T09:57:09.292906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02573","created_at":"2026-07-05T09:57:09.292906+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7SWU3XHZ3UB","created_at":"2026-07-05T09:57:09.292906+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7SWU3XHZ3UBVUNT","created_at":"2026-07-05T09:57:09.292906+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7SWU3XH","created_at":"2026-07-05T09:57:09.292906+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/T7SWU3XHZ3UBVUNTCP4KAMT7HY","json":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY.json","graph_json":"https://pith.science/api/pith-number/T7SWU3XHZ3UBVUNTCP4KAMT7HY/graph.json","events_json":"https://pith.science/api/pith-number/T7SWU3XHZ3UBVUNTCP4KAMT7HY/events.json","paper":"https://pith.science/paper/T7SWU3XH"},"agent_actions":{"view_html":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY","download_json":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY.json","view_paper":"https://pith.science/paper/T7SWU3XH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02573&json=true","fetch_graph":"https://pith.science/api/pith-number/T7SWU3XHZ3UBVUNTCP4KAMT7HY/graph.json","fetch_events":"https://pith.science/api/pith-number/T7SWU3XHZ3UBVUNTCP4KAMT7HY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY/action/storage_attestation","attest_author":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY/action/author_attestation","sign_citation":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY/action/citation_signature","submit_replication":"https://pith.science/pith/T7SWU3XHZ3UBVUNTCP4KAMT7HY/action/replication_record"}},"created_at":"2026-07-05T09:57:09.292906+00:00","updated_at":"2026-07-05T09:57:09.292906+00:00"}