{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KMYLMJKJVSWLDZRERG3YAQL5JV","short_pith_number":"pith:KMYLMJKJ","schema_version":"1.0","canonical_sha256":"5330b62549acacb1e62489b780417d4d6d165b2f55b58f54d2562049736c493b","source":{"kind":"arxiv","id":"2508.05851","version":1},"attestation_state":"computed","paper":{"title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danail Stoyanov, Evangelos B. Mazomenos, Felix J. S. Bragman, Imanol Luengo, Jialang Xu, Ka-Wai Yung","submitted_at":"2025-08-07T20:52:49Z","abstract_excerpt":"Vision Transformers have substantially advanced the capabilities of segmentation models across both image and video domains. Among them, the Swin Transformer stands out for its ability to capture hierarchical, multi-scale representations, making it a popular backbone for segmentation in videos. However, despite its window-attention scheme, it still incurs a high computational cost, especially in larger variants commonly used for dense prediction in videos. This remains a major bottleneck for real-time, resource-constrained applications. Whilst token reduction methods have been proposed to alle"},"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":"2508.05851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T20:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"0af98788a9066fff9d84cf9abe6de4705d9ac4bc112b7f33131ead93ad200743","abstract_canon_sha256":"14918eb46c08798b01e99db15f9f995b88c1e5afecbe3c5b3abacd7ac60e96a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:44.384441Z","signature_b64":"bhQfpcjjnXJ1tqR96xWmoTInq0AxH6yK22kAJdCttrrYFS08X6aH+tEulSZN6QOxheBJVUoX0Pg+KHgTbrHoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5330b62549acacb1e62489b780417d4d6d165b2f55b58f54d2562049736c493b","last_reissued_at":"2026-07-05T11:50:44.383946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:44.383946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danail Stoyanov, Evangelos B. Mazomenos, Felix J. S. Bragman, Imanol Luengo, Jialang Xu, Ka-Wai Yung","submitted_at":"2025-08-07T20:52:49Z","abstract_excerpt":"Vision Transformers have substantially advanced the capabilities of segmentation models across both image and video domains. Among them, the Swin Transformer stands out for its ability to capture hierarchical, multi-scale representations, making it a popular backbone for segmentation in videos. However, despite its window-attention scheme, it still incurs a high computational cost, especially in larger variants commonly used for dense prediction in videos. This remains a major bottleneck for real-time, resource-constrained applications. Whilst token reduction methods have been proposed to alle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05851","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/2508.05851/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":"2508.05851","created_at":"2026-07-05T11:50:44.384005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05851v1","created_at":"2026-07-05T11:50:44.384005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05851","created_at":"2026-07-05T11:50:44.384005+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMYLMJKJVSWL","created_at":"2026-07-05T11:50:44.384005+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMYLMJKJVSWLDZRE","created_at":"2026-07-05T11:50:44.384005+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMYLMJKJ","created_at":"2026-07-05T11:50:44.384005+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/KMYLMJKJVSWLDZRERG3YAQL5JV","json":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV.json","graph_json":"https://pith.science/api/pith-number/KMYLMJKJVSWLDZRERG3YAQL5JV/graph.json","events_json":"https://pith.science/api/pith-number/KMYLMJKJVSWLDZRERG3YAQL5JV/events.json","paper":"https://pith.science/paper/KMYLMJKJ"},"agent_actions":{"view_html":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV","download_json":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV.json","view_paper":"https://pith.science/paper/KMYLMJKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05851&json=true","fetch_graph":"https://pith.science/api/pith-number/KMYLMJKJVSWLDZRERG3YAQL5JV/graph.json","fetch_events":"https://pith.science/api/pith-number/KMYLMJKJVSWLDZRERG3YAQL5JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV/action/storage_attestation","attest_author":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV/action/author_attestation","sign_citation":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV/action/citation_signature","submit_replication":"https://pith.science/pith/KMYLMJKJVSWLDZRERG3YAQL5JV/action/replication_record"}},"created_at":"2026-07-05T11:50:44.384005+00:00","updated_at":"2026-07-05T11:50:44.384005+00:00"}