{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FU5LD5PBRQCCVDUHN5DKCACDRZ","short_pith_number":"pith:FU5LD5PB","schema_version":"1.0","canonical_sha256":"2d3ab1f5e18c042a8e876f46a100438e7d87911784f35f95419185568de4d0c4","source":{"kind":"arxiv","id":"2605.20977","version":1},"attestation_state":"computed","paper":{"title":"Parallel Context Modeling for Sliding Window Attention in Neural Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Alexander Kopte, Andr\\'e Kaup","submitted_at":"2026-05-20T10:06:23Z","abstract_excerpt":"Most neural video codecs rely on temporal conditioning, which makes them susceptible to error propagation over long sequences. While Transformer-based architectures like the VCT offer a drift-free alternative, they suffer from high computational complexity and inferior RD performance. The recent SWA addresses these shortcomings by reducing complexity and enhancing RD performance, yet it restricts decoding to a strictly sequential raster-scan order, creating a critical bottleneck in decoding latency. To resolve this, we propose P-SWA, utilizing diagonal wavefronts to enable parallel decoding. B"},"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":"2605.20977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2026-05-20T10:06:23Z","cross_cats_sorted":[],"title_canon_sha256":"9b4efd6f985d7720fa2c17a4bbf4c4bc41c4a4446328cddd5aeb6212f37ce036","abstract_canon_sha256":"3a1897662476edcc1ef7e2ea7ab0d6edd7c65764740b144090f5e7fc773affe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:30.730533Z","signature_b64":"nAlpgJ/Nx+mGc9PY+9bavdF5ButHK/r3OTn1hzelLwNbr15dhU8oWKtozJgiXSTHVA3LlnpFNIyBr/xfoW8KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3ab1f5e18c042a8e876f46a100438e7d87911784f35f95419185568de4d0c4","last_reissued_at":"2026-05-21T01:05:30.730033Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:30.730033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Context Modeling for Sliding Window Attention in Neural Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Alexander Kopte, Andr\\'e Kaup","submitted_at":"2026-05-20T10:06:23Z","abstract_excerpt":"Most neural video codecs rely on temporal conditioning, which makes them susceptible to error propagation over long sequences. While Transformer-based architectures like the VCT offer a drift-free alternative, they suffer from high computational complexity and inferior RD performance. The recent SWA addresses these shortcomings by reducing complexity and enhancing RD performance, yet it restricts decoding to a strictly sequential raster-scan order, creating a critical bottleneck in decoding latency. To resolve this, we propose P-SWA, utilizing diagonal wavefronts to enable parallel decoding. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20977","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/2605.20977/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":"2605.20977","created_at":"2026-05-21T01:05:30.730105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20977v1","created_at":"2026-05-21T01:05:30.730105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20977","created_at":"2026-05-21T01:05:30.730105+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU5LD5PBRQCC","created_at":"2026-05-21T01:05:30.730105+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU5LD5PBRQCCVDUH","created_at":"2026-05-21T01:05:30.730105+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU5LD5PB","created_at":"2026-05-21T01:05:30.730105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20977","citing_title":"Parallel Context Modeling for Sliding Window Attention in Neural Video Coding","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ","json":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ.json","graph_json":"https://pith.science/api/pith-number/FU5LD5PBRQCCVDUHN5DKCACDRZ/graph.json","events_json":"https://pith.science/api/pith-number/FU5LD5PBRQCCVDUHN5DKCACDRZ/events.json","paper":"https://pith.science/paper/FU5LD5PB"},"agent_actions":{"view_html":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ","download_json":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ.json","view_paper":"https://pith.science/paper/FU5LD5PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20977&json=true","fetch_graph":"https://pith.science/api/pith-number/FU5LD5PBRQCCVDUHN5DKCACDRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FU5LD5PBRQCCVDUHN5DKCACDRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ/action/storage_attestation","attest_author":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ/action/author_attestation","sign_citation":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ/action/citation_signature","submit_replication":"https://pith.science/pith/FU5LD5PBRQCCVDUHN5DKCACDRZ/action/replication_record"}},"created_at":"2026-05-21T01:05:30.730105+00:00","updated_at":"2026-05-21T01:05:30.730105+00:00"}