{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IOYLS5SGOEE2N7EKG2NDU64GWS","short_pith_number":"pith:IOYLS5SG","canonical_record":{"source":{"id":"2605.13182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:41:48Z","cross_cats_sorted":[],"title_canon_sha256":"f0141a251e1702a0a7369dbaebce57b12d0f114fac819a0d6706da2f21a4dd78","abstract_canon_sha256":"1062a9489460a1a9f687702a6a080659b47193ce4423797260d6ce0dd4eb237a"},"schema_version":"1.0"},"canonical_sha256":"43b0b976467109a6fc8a369a3a7b86b489cc151c44f2cfef2de11046ce3e23ca","source":{"kind":"arxiv","id":"2605.13182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13182","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13182v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13182","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"IOYLS5SGOEE2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IOYLS5SGOEE2N7EK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IOYLS5SG","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IOYLS5SGOEE2N7EKG2NDU64GWS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:41:48Z","cross_cats_sorted":[],"title_canon_sha256":"f0141a251e1702a0a7369dbaebce57b12d0f114fac819a0d6706da2f21a4dd78","abstract_canon_sha256":"1062a9489460a1a9f687702a6a080659b47193ce4423797260d6ce0dd4eb237a"},"schema_version":"1.0"},"canonical_sha256":"43b0b976467109a6fc8a369a3a7b86b489cc151c44f2cfef2de11046ce3e23ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:56.346277Z","signature_b64":"gyyUMiLl+DotPd5jkPpTKCZy0G8yktLC80GtZ5IX2tKRK7WfCSkvIGNrwvL4oJQDoafFDgA9bnwufsrrlY9TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b0b976467109a6fc8a369a3a7b86b489cc151c44f2cfef2de11046ce3e23ca","last_reissued_at":"2026-05-18T03:08:56.345543Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:56.345543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13182","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+FC1bvTiganCUwLMfB18eVkL+FoDk46koPmW3ZvMTNR77rkqZ6GcnqFcG3eO63UXwrj6ETCKZez8Fh/O92OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:54:39.427304Z"},"content_sha256":"d724af3114ab70b04a12344aeba6d3a67eb3549e117b1bb3ef8e6dffcfce5181","schema_version":"1.0","event_id":"sha256:d724af3114ab70b04a12344aeba6d3a67eb3549e117b1bb3ef8e6dffcfce5181"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IOYLS5SGOEE2N7EKG2NDU64GWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming He, Dehua Song, Jin Han, Ruofan Yang, Yong Guo, Yulun Zhang, Zheng Chen, Zichen Zou","submitted_at":"2026-05-13T08:41:48Z","abstract_excerpt":"Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-resolution (STVSR) setting remains limited. Existing diffusion-based STVSR approaches suffer from two issues: (1) low inference efficiency and (2) insufficient utilization of spatiotemporal information. These limitations impede deployment. To address these issues, we introduce DiffST, an efficient spatiotemporal-aware video diffusion framework for real-world STVSR. To improve efficiency, we adapt a pre-trained diffus"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17× faster than previous diffusion-based STVSR methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That adapting a pre-trained image diffusion model to one-step sampling on entire videos, combined with the proposed CFCA and VRG modules, will preserve or improve quality without introducing artifacts specific to real-world degradations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"04c61a46452e9658c5dcc5ea3aa4a0e97a0cc40b05b40c0b37df4ba8395e74ee"},"source":{"id":"2605.13182","kind":"arxiv","version":1},"verdict":{"id":"d836683e-0fa2-4d77-ac11-5a0872d955b2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:26:21.353988Z","strongest_claim":"Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17× faster than previous diffusion-based STVSR methods.","one_line_summary":"DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That adapting a pre-trained image diffusion model to one-step sampling on entire videos, combined with the proposed CFCA and VRG modules, will preserve or improve quality without introducing artifacts specific to real-world degradations.","pith_extraction_headline":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster."},"references":{"count":65,"sample":[{"doi":"","year":2022,"title":"Towards interpretable video super-resolution via alternating optimization","work_id":"b6438ad2-a647-4d09-b19b-9c01aec48269","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Basicvsr: The search for essential components in video super-resolution and beyond","work_id":"56e6bda2-3197-4b81-baa1-b8b0b25fb8c6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Basicvsr++: Improving video super-resolution with enhanced propagation and alignment","work_id":"d9b04ae3-7d4d-4aa6-8be9-398d4ef7f072","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Investigating tradeoffs in real-world video super-resolution","work_id":"778cf319-6407-47f3-8cda-2ca81518103a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Motif: Learning motion trajectories with local implicit neural functions for continuous space-time video super-resolution","work_id":"957198b7-cb16-4a1a-8dbe-f9270fbbfb98","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"934d442b18378dedbe13ac19cbffff1c8a454cefea264feb9141e2c13bb02570","internal_anchors":2},"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":"d836683e-0fa2-4d77-ac11-5a0872d955b2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QUXM3ZdQatV3m1Fq45oyKqaca/IZ1KKiYHpxKBApkfFwjcGJdVzd+LpGthIBspTN0ekAWEN0aTejB2yrePvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:54:39.428360Z"},"content_sha256":"3435db0a00515479dbc8a0937da68e4ee69c723df0373dada5b26137c3e96698","schema_version":"1.0","event_id":"sha256:3435db0a00515479dbc8a0937da68e4ee69c723df0373dada5b26137c3e96698"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/bundle.json","state_url":"https://pith.science/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/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":"2026-05-28T22:54:39Z","links":{"resolver":"https://pith.science/pith/IOYLS5SGOEE2N7EKG2NDU64GWS","bundle":"https://pith.science/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/bundle.json","state":"https://pith.science/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOYLS5SGOEE2N7EKG2NDU64GWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IOYLS5SGOEE2N7EKG2NDU64GWS","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":"1062a9489460a1a9f687702a6a080659b47193ce4423797260d6ce0dd4eb237a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:41:48Z","title_canon_sha256":"f0141a251e1702a0a7369dbaebce57b12d0f114fac819a0d6706da2f21a4dd78"},"schema_version":"1.0","source":{"id":"2605.13182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13182","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13182v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13182","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"IOYLS5SGOEE2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IOYLS5SGOEE2N7EK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IOYLS5SG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3435db0a00515479dbc8a0937da68e4ee69c723df0373dada5b26137c3e96698","target":"graph","created_at":"2026-05-18T03:08:56Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17× faster than previous diffusion-based STVSR methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That adapting a pre-trained image diffusion model to one-step sampling on entire videos, combined with the proposed CFCA and VRG modules, will preserve or improve quality without introducing artifacts specific to real-world degradations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster."}],"snapshot_sha256":"04c61a46452e9658c5dcc5ea3aa4a0e97a0cc40b05b40c0b37df4ba8395e74ee"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-resolution (STVSR) setting remains limited. Existing diffusion-based STVSR approaches suffer from two issues: (1) low inference efficiency and (2) insufficient utilization of spatiotemporal information. These limitations impede deployment. To address these issues, we introduce DiffST, an efficient spatiotemporal-aware video diffusion framework for real-world STVSR. To improve efficiency, we adapt a pre-trained diffus","authors_text":"Chunming He, Dehua Song, Jin Han, Ruofan Yang, Yong Guo, Yulun Zhang, Zheng Chen, Zichen Zou","cross_cats":[],"headline":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:41:48Z","title":"DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution"},"references":{"count":65,"internal_anchors":2,"resolved_work":65,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Towards interpretable video super-resolution via alternating optimization","work_id":"b6438ad2-a647-4d09-b19b-9c01aec48269","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Basicvsr: The search for essential components in video super-resolution and beyond","work_id":"56e6bda2-3197-4b81-baa1-b8b0b25fb8c6","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Basicvsr++: Improving video super-resolution with enhanced propagation and alignment","work_id":"d9b04ae3-7d4d-4aa6-8be9-398d4ef7f072","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Investigating tradeoffs in real-world video super-resolution","work_id":"778cf319-6407-47f3-8cda-2ca81518103a","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Motif: Learning motion trajectories with local implicit neural functions for continuous space-time video super-resolution","work_id":"957198b7-cb16-4a1a-8dbe-f9270fbbfb98","year":2023}],"snapshot_sha256":"934d442b18378dedbe13ac19cbffff1c8a454cefea264feb9141e2c13bb02570"},"source":{"id":"2605.13182","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:26:21.353988Z","id":"d836683e-0fa2-4d77-ac11-5a0872d955b2","model_set":{"reader":"grok-4.3"},"one_line_summary":"DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DiffST adapts pre-trained diffusion models for one-step whole-video sampling to lead real-world space-time super-resolution while running 17 times faster.","strongest_claim":"Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17× faster than previous diffusion-based STVSR methods.","weakest_assumption":"That adapting a pre-trained image diffusion model to one-step sampling on entire videos, combined with the proposed CFCA and VRG modules, will preserve or improve quality without introducing artifacts specific to real-world degradations."}},"verdict_id":"d836683e-0fa2-4d77-ac11-5a0872d955b2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d724af3114ab70b04a12344aeba6d3a67eb3549e117b1bb3ef8e6dffcfce5181","target":"record","created_at":"2026-05-18T03:08:56Z","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":"1062a9489460a1a9f687702a6a080659b47193ce4423797260d6ce0dd4eb237a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:41:48Z","title_canon_sha256":"f0141a251e1702a0a7369dbaebce57b12d0f114fac819a0d6706da2f21a4dd78"},"schema_version":"1.0","source":{"id":"2605.13182","kind":"arxiv","version":1}},"canonical_sha256":"43b0b976467109a6fc8a369a3a7b86b489cc151c44f2cfef2de11046ce3e23ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b0b976467109a6fc8a369a3a7b86b489cc151c44f2cfef2de11046ce3e23ca","first_computed_at":"2026-05-18T03:08:56.345543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:56.345543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gyyUMiLl+DotPd5jkPpTKCZy0G8yktLC80GtZ5IX2tKRK7WfCSkvIGNrwvL4oJQDoafFDgA9bnwufsrrlY9TCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:56.346277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d724af3114ab70b04a12344aeba6d3a67eb3549e117b1bb3ef8e6dffcfce5181","sha256:3435db0a00515479dbc8a0937da68e4ee69c723df0373dada5b26137c3e96698"],"state_sha256":"b0decebf23bec06e853a761d4449897bbf4d7b8c6b5a3f7667c647b5430fcd04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l79CKFfq5/VJ4fiGGy22WypRzw15J33EEptZQugIVDgTTr8FCpCh+c6MvIW7AeRG/CQmE4jeXPiWjEoldqC5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:54:39.432368Z","bundle_sha256":"5c19d879fd16e58d307aeb17c1d6541463c65bc066d8d6d20890b5e62a9cd4bd"}}