{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SY6GQXC2LJRDA7XBVDRZFJBBPN","short_pith_number":"pith:SY6GQXC2","schema_version":"1.0","canonical_sha256":"963c685c5a5a62307ee1a8e392a4217b429faf5a7aa3a63d5d69b4d715d02046","source":{"kind":"arxiv","id":"2605.16579","version":1},"attestation_state":"computed","paper":{"title":"Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kunyang Li, Mubarak Shah, Yuzhang Shang","submitted_at":"2026-05-15T19:33:45Z","abstract_excerpt":"Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to key-value caching, which limits its scalability to long video horizons. Existing remedies (e.g., sparse attention and KV-cache compression) reduce per-step cost but still rely on a linearly growing cache or irreversibly discard past context, and thus fail to address linear memory growth and streaming context management. To address this scalability bottleneck, we"},"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":"2605.16579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T19:33:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"153fd39f8fee8dcad499f291ec5d1564d88e5e4d5f9255cd22fa53090f0c5477","abstract_canon_sha256":"e4ded70fb4342ca1f9ef3f622b5f7f9e53d26abe20b76da60887b5686ed50d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:30.751124Z","signature_b64":"U2hzCm+Jlwm1iehnOQPUUfwkXOuMxYTZk5bKKwJx79V4oaQ3gAIovglXZ+Y9SmtI2E89h0awyK3VZA2r6zpLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"963c685c5a5a62307ee1a8e392a4217b429faf5a7aa3a63d5d69b4d715d02046","last_reissued_at":"2026-05-20T00:02:30.750265Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:30.750265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kunyang Li, Mubarak Shah, Yuzhang Shang","submitted_at":"2026-05-15T19:33:45Z","abstract_excerpt":"Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to key-value caching, which limits its scalability to long video horizons. Existing remedies (e.g., sparse attention and KV-cache compression) reduce per-step cost but still rely on a linearly growing cache or irreversibly discard past context, and thus fail to address linear memory growth and streaming context management. To address this scalability bottleneck, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16579","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/2605.16579/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.854130Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.614701Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"dc5a9ba7c1f978b544ce30b3fa890b534982401241a977489ba546961ce9244e"},"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":"2605.16579","created_at":"2026-05-20T00:02:30.750405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16579v1","created_at":"2026-05-20T00:02:30.750405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16579","created_at":"2026-05-20T00:02:30.750405+00:00"},{"alias_kind":"pith_short_12","alias_value":"SY6GQXC2LJRD","created_at":"2026-05-20T00:02:30.750405+00:00"},{"alias_kind":"pith_short_16","alias_value":"SY6GQXC2LJRDA7XB","created_at":"2026-05-20T00:02:30.750405+00:00"},{"alias_kind":"pith_short_8","alias_value":"SY6GQXC2","created_at":"2026-05-20T00:02:30.750405+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/SY6GQXC2LJRDA7XBVDRZFJBBPN","json":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN.json","graph_json":"https://pith.science/api/pith-number/SY6GQXC2LJRDA7XBVDRZFJBBPN/graph.json","events_json":"https://pith.science/api/pith-number/SY6GQXC2LJRDA7XBVDRZFJBBPN/events.json","paper":"https://pith.science/paper/SY6GQXC2"},"agent_actions":{"view_html":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN","download_json":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN.json","view_paper":"https://pith.science/paper/SY6GQXC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16579&json=true","fetch_graph":"https://pith.science/api/pith-number/SY6GQXC2LJRDA7XBVDRZFJBBPN/graph.json","fetch_events":"https://pith.science/api/pith-number/SY6GQXC2LJRDA7XBVDRZFJBBPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN/action/storage_attestation","attest_author":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN/action/author_attestation","sign_citation":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN/action/citation_signature","submit_replication":"https://pith.science/pith/SY6GQXC2LJRDA7XBVDRZFJBBPN/action/replication_record"}},"created_at":"2026-05-20T00:02:30.750405+00:00","updated_at":"2026-05-20T00:02:30.750405+00:00"}