{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RLTDOVVVMXOL2QL6DKTB4ZA4U7","short_pith_number":"pith:RLTDOVVV","canonical_record":{"source":{"id":"2406.07368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T15:34:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"41d539096927a3d7a04a8e86287a247fd736595934a10a2a20a400b3d923ccb5","abstract_canon_sha256":"e51dee7e4d7f3137f41fa71de743ff7b89bcec0daaed0812d9596e545e3d01ee"},"schema_version":"1.0"},"canonical_sha256":"8ae63756b565dcbd417e1aa61e641ca7d170f546f5a2573e0145f98614e213f3","source":{"kind":"arxiv","id":"2406.07368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07368","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07368v2","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07368","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"RLTDOVVVMXOL","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"RLTDOVVVMXOL2QL6","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"RLTDOVVV","created_at":"2026-07-05T08:48:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RLTDOVVVMXOL2QL6DKTB4ZA4U7","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T15:34:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"41d539096927a3d7a04a8e86287a247fd736595934a10a2a20a400b3d923ccb5","abstract_canon_sha256":"e51dee7e4d7f3137f41fa71de743ff7b89bcec0daaed0812d9596e545e3d01ee"},"schema_version":"1.0"},"canonical_sha256":"8ae63756b565dcbd417e1aa61e641ca7d170f546f5a2573e0145f98614e213f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:32.066608Z","signature_b64":"nvak0+9gliahQ8IRb0NlA3bvnEfuypohdbsl61rDB4NBuGiMwHUG7laz7MtjLqNAlvtyaNg5mkUIZC4l/jujDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae63756b565dcbd417e1aa61e641ca7d170f546f5a2573e0145f98614e213f3","last_reissued_at":"2026-07-05T08:48:32.066090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:32.066090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07368","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PojTkGunp32gJzBr7kIiAhMTvRi38u9solxuU19ErREUWRZ0/g2wB/R7IBWuJqcBgbZ+/EAn0gvJat6If63FBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:11.597229Z"},"content_sha256":"20ed2fd0cc48b6d4890bb3778733bd8ddcf27d5a2f32c38609ff58b5ae2d94b1","schema_version":"1.0","event_id":"sha256:20ed2fd0cc48b6d4890bb3778733bd8ddcf27d5a2f32c38609ff58b5ae2d94b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RLTDOVVVMXOL2QL6DKTB4ZA4U7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir Yazdanbakhsh, Haoran You, Yichao Fu, Yingyan Celine Lin, Zheng Wang","submitted_at":"2024-06-11T15:34:43Z","abstract_excerpt":"Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency due to the sequential processing nature of autoregressive LLMs during generation. While linear attention and speculative decoding offer potential solutions, their applicability and synergistic potential for enhancing autoregressive LLMs remain uncertain. We conduct the first comprehensive study on the efficacy of existing linear attention methods for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07368","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/2406.07368/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzllyFcV/m2u8zg/fT9gQbcWHKQriFknaWz7zSmFXSywkh+IIquriUR0qwQ8oxhMlAfJ+l4034gbtd57qqwxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:11.597623Z"},"content_sha256":"acd49e5e5fa0909bf92d6724c3ad3dea5e90569fb96d9eb683874eee7aa91d98","schema_version":"1.0","event_id":"sha256:acd49e5e5fa0909bf92d6724c3ad3dea5e90569fb96d9eb683874eee7aa91d98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/bundle.json","state_url":"https://pith.science/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:38:11Z","links":{"resolver":"https://pith.science/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7","bundle":"https://pith.science/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/bundle.json","state":"https://pith.science/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLTDOVVVMXOL2QL6DKTB4ZA4U7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLTDOVVVMXOL2QL6DKTB4ZA4U7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e51dee7e4d7f3137f41fa71de743ff7b89bcec0daaed0812d9596e545e3d01ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T15:34:43Z","title_canon_sha256":"41d539096927a3d7a04a8e86287a247fd736595934a10a2a20a400b3d923ccb5"},"schema_version":"1.0","source":{"id":"2406.07368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07368","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07368v2","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07368","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"RLTDOVVVMXOL","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"RLTDOVVVMXOL2QL6","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"RLTDOVVV","created_at":"2026-07-05T08:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:acd49e5e5fa0909bf92d6724c3ad3dea5e90569fb96d9eb683874eee7aa91d98","target":"graph","created_at":"2026-07-05T08:48:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.07368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency due to the sequential processing nature of autoregressive LLMs during generation. While linear attention and speculative decoding offer potential solutions, their applicability and synergistic potential for enhancing autoregressive LLMs remain uncertain. We conduct the first comprehensive study on the efficacy of existing linear attention methods for","authors_text":"Amir Yazdanbakhsh, Haoran You, Yichao Fu, Yingyan Celine Lin, Zheng Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T15:34:43Z","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07368","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:20ed2fd0cc48b6d4890bb3778733bd8ddcf27d5a2f32c38609ff58b5ae2d94b1","target":"record","created_at":"2026-07-05T08:48:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e51dee7e4d7f3137f41fa71de743ff7b89bcec0daaed0812d9596e545e3d01ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T15:34:43Z","title_canon_sha256":"41d539096927a3d7a04a8e86287a247fd736595934a10a2a20a400b3d923ccb5"},"schema_version":"1.0","source":{"id":"2406.07368","kind":"arxiv","version":2}},"canonical_sha256":"8ae63756b565dcbd417e1aa61e641ca7d170f546f5a2573e0145f98614e213f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ae63756b565dcbd417e1aa61e641ca7d170f546f5a2573e0145f98614e213f3","first_computed_at":"2026-07-05T08:48:32.066090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:32.066090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nvak0+9gliahQ8IRb0NlA3bvnEfuypohdbsl61rDB4NBuGiMwHUG7laz7MtjLqNAlvtyaNg5mkUIZC4l/jujDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:32.066608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20ed2fd0cc48b6d4890bb3778733bd8ddcf27d5a2f32c38609ff58b5ae2d94b1","sha256:acd49e5e5fa0909bf92d6724c3ad3dea5e90569fb96d9eb683874eee7aa91d98"],"state_sha256":"9c655c3faa0e8132d728fb8949e504458f5dd6fbad8f087bf5c8344067e960db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIOPduWstLjYA71lqU1xiVabJV8Tagu98YUtVFaOMBg1Ns50CA1smKsmoypnRuUCnKIRzFgMVbyhA90Qbi/wAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:38:11.599527Z","bundle_sha256":"3c672ac778fea43ed42622f9e9226906b026258e144e462e1337e9bd77173ca6"}}