{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GUS36IWY2KZFRK7IM5RIKQ24VE","short_pith_number":"pith:GUS36IWY","canonical_record":{"source":{"id":"2605.14267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:11:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a2702a0981d81ef7aba76c0ab528ca84d7fb0a296e5f54e6572af9574ed46350","abstract_canon_sha256":"893ca7fde587799ed9ab6dfd4b926f0f30982442fd7463af5d4e823bb8b8b03d"},"schema_version":"1.0"},"canonical_sha256":"3525bf22d8d2b258abe8676285435ca91eb9bf3b8527a7dad44a46a192ac91d5","source":{"kind":"arxiv","id":"2605.14267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14267","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14267v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14267","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"GUS36IWY2KZF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GUS36IWY2KZFRK7I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GUS36IWY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GUS36IWY2KZFRK7IM5RIKQ24VE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:11:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a2702a0981d81ef7aba76c0ab528ca84d7fb0a296e5f54e6572af9574ed46350","abstract_canon_sha256":"893ca7fde587799ed9ab6dfd4b926f0f30982442fd7463af5d4e823bb8b8b03d"},"schema_version":"1.0"},"canonical_sha256":"3525bf22d8d2b258abe8676285435ca91eb9bf3b8527a7dad44a46a192ac91d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.431108Z","signature_b64":"ouEfMJuV7ZRmHFw9gKy4TIM8aRV7FrJKGoxkONJ9JW50CJAy2eskXwT3kcPqQylRS8Vz9ginmO2WCyTwrbVeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3525bf22d8d2b258abe8676285435ca91eb9bf3b8527a7dad44a46a192ac91d5","last_reissued_at":"2026-05-17T23:39:10.430640Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.430640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14267","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":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNQPuAzKo4aBJ2xJ3MMntnZ885stE4F8huMcQnME2w5De6sacdOrM8asGhf2SzX2rez/iJF5KqURO/5ELBXPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:28:25.376394Z"},"content_sha256":"0bc606b37d817b455e517868d011182e2cc0d290ad34b94153b5955928e83974","schema_version":"1.0","event_id":"sha256:0bc606b37d817b455e517868d011182e2cc0d290ad34b94153b5955928e83974"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GUS36IWY2KZFRK7IM5RIKQ24VE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Restoration via Diffusion Models with Dynamic Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Wen Li, Yang Zheng, Zhaoqiang Liu","submitted_at":"2026-05-14T02:11:47Z","abstract_excerpt":"Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods based on latent DMs seek to alleviate this issue by utilizing the compressed latent space of a variational autoencoder, they require repeated encoder-decoder inference. This introduces significant additional computational burdens, often resulting in runtime performance that is even inferior to that of their pixel-space counterparts. To mitigate the computation"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Empirical evaluations across diverse image datasets and various restoration tasks demonstrate that the proposed methods outperform recent DM-based approaches in the majority of experimental scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That fine-tuning pre-trained diffusion models for dynamic resolution priors preserves sufficient information in the lower-dimensional subspaces to maintain or improve reconstruction fidelity without introducing new artifacts or loss of detail.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"87b77bb3ec24ad74aa9b50e136134e7e849f864eaa0dea001b9176ea4bb9531a"},"source":{"id":"2605.14267","kind":"arxiv","version":1},"verdict":{"id":"afe0e8cd-588f-464a-afb9-9450f336f47a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:50:30.810193Z","strongest_claim":"Empirical evaluations across diverse image datasets and various restoration tasks demonstrate that the proposed methods outperform recent DM-based approaches in the majority of experimental scenarios.","one_line_summary":"Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That fine-tuning pre-trained diffusion models for dynamic resolution priors preserves sufficient information in the lower-dimensional subspaces to maintain or improve reconstruction fidelity without introducing new artifacts or loss of detail.","pith_extraction_headline":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration."},"references":{"count":15,"sample":[{"doi":"","year":2017,"title":"Agustsson, E. and Timofte, R. NTIRE 2017 challenge on single image super-resolution: Dataset and study. In CVPRW,","work_id":"0db44895-0daa-4eac-9171-1f934f485c3f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Provable diffusion posterior sampling for Bayesian inversion.arXiv preprint arXiv:2512.08022","work_id":"6f57e135-52a0-4385-848b-44e656f3d4fc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing","work_id":"6df381c8-8718-47a8-9e55-a3c7b5aac3ca","ref_index":3,"cited_arxiv_id":"2511.17038","is_internal_anchor":true},{"doi":"","year":null,"title":"A Survey on Diffusion Models for Inverse Problems","work_id":"f2cbc6cc-8d87-4b5d-9751-74f49d4e3b63","ref_index":4,"cited_arxiv_id":"2410.00083","is_internal_anchor":true},{"doi":"","year":null,"title":"Robust posterior diffusion-based sampling via adaptive guidance scale.arXiv preprint arXiv:2511.18471,","work_id":"c73020fa-5f06-42ea-82d5-54ef1c3f0a6d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"f948231cf5c9eca85e2292694a781233ffe99368a23b29f9eec27884251457db","internal_anchors":3},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ea2195a689049373a049d4d32ec36f844d743e9c1d4b0d9bccbd06d97abb24b8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"afe0e8cd-588f-464a-afb9-9450f336f47a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"811QRDL9x9JymOLCLSNlTm/KD/irL7s87j66VGOUKKS3+UH/7e7Fv0wGwxrNX9rbpWdIT9m96Dw44VdBQJLwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:28:25.376941Z"},"content_sha256":"5233ba3a0b1b677f8cdd9c306b1ecca464e5a1df7a51f8b682d8ff70de2e1580","schema_version":"1.0","event_id":"sha256:5233ba3a0b1b677f8cdd9c306b1ecca464e5a1df7a51f8b682d8ff70de2e1580"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/bundle.json","state_url":"https://pith.science/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/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":"2026-05-30T19:28:25Z","links":{"resolver":"https://pith.science/pith/GUS36IWY2KZFRK7IM5RIKQ24VE","bundle":"https://pith.science/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/bundle.json","state":"https://pith.science/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUS36IWY2KZFRK7IM5RIKQ24VE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUS36IWY2KZFRK7IM5RIKQ24VE","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":"893ca7fde587799ed9ab6dfd4b926f0f30982442fd7463af5d4e823bb8b8b03d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:11:47Z","title_canon_sha256":"a2702a0981d81ef7aba76c0ab528ca84d7fb0a296e5f54e6572af9574ed46350"},"schema_version":"1.0","source":{"id":"2605.14267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14267","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14267v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14267","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"GUS36IWY2KZF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GUS36IWY2KZFRK7I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GUS36IWY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5233ba3a0b1b677f8cdd9c306b1ecca464e5a1df7a51f8b682d8ff70de2e1580","target":"graph","created_at":"2026-05-17T23:39:10Z","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":"Empirical evaluations across diverse image datasets and various restoration tasks demonstrate that the proposed methods outperform recent DM-based approaches in the majority of experimental scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That fine-tuning pre-trained diffusion models for dynamic resolution priors preserves sufficient information in the lower-dimensional subspaces to maintain or improve reconstruction fidelity without introducing new artifacts or loss of detail."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration."}],"snapshot_sha256":"87b77bb3ec24ad74aa9b50e136134e7e849f864eaa0dea001b9176ea4bb9531a"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ea2195a689049373a049d4d32ec36f844d743e9c1d4b0d9bccbd06d97abb24b8"},"paper":{"abstract_excerpt":"Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods based on latent DMs seek to alleviate this issue by utilizing the compressed latent space of a variational autoencoder, they require repeated encoder-decoder inference. This introduces significant additional computational burdens, often resulting in runtime performance that is even inferior to that of their pixel-space counterparts. To mitigate the computation","authors_text":"Wen Li, Yang Zheng, Zhaoqiang Liu","cross_cats":["cs.AI"],"headline":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:11:47Z","title":"Image Restoration via Diffusion Models with Dynamic Resolution"},"references":{"count":15,"internal_anchors":3,"resolved_work":15,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Agustsson, E. and Timofte, R. NTIRE 2017 challenge on single image super-resolution: Dataset and study. In CVPRW,","work_id":"0db44895-0daa-4eac-9171-1f934f485c3f","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Provable diffusion posterior sampling for Bayesian inversion.arXiv preprint arXiv:2512.08022","work_id":"6f57e135-52a0-4385-848b-44e656f3d4fc","year":null},{"cited_arxiv_id":"2511.17038","doi":"","is_internal_anchor":true,"ref_index":3,"title":"DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing","work_id":"6df381c8-8718-47a8-9e55-a3c7b5aac3ca","year":null},{"cited_arxiv_id":"2410.00083","doi":"","is_internal_anchor":true,"ref_index":4,"title":"A Survey on Diffusion Models for Inverse Problems","work_id":"f2cbc6cc-8d87-4b5d-9751-74f49d4e3b63","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Robust posterior diffusion-based sampling via adaptive guidance scale.arXiv preprint arXiv:2511.18471,","work_id":"c73020fa-5f06-42ea-82d5-54ef1c3f0a6d","year":null}],"snapshot_sha256":"f948231cf5c9eca85e2292694a781233ffe99368a23b29f9eec27884251457db"},"source":{"id":"2605.14267","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:50:30.810193Z","id":"afe0e8cd-588f-464a-afb9-9450f336f47a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Dynamic resolution diffusion models project images into lower-dimensional subspaces to speed up restoration.","strongest_claim":"Empirical evaluations across diverse image datasets and various restoration tasks demonstrate that the proposed methods outperform recent DM-based approaches in the majority of experimental scenarios.","weakest_assumption":"That fine-tuning pre-trained diffusion models for dynamic resolution priors preserves sufficient information in the lower-dimensional subspaces to maintain or improve reconstruction fidelity without introducing new artifacts or loss of detail."}},"verdict_id":"afe0e8cd-588f-464a-afb9-9450f336f47a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0bc606b37d817b455e517868d011182e2cc0d290ad34b94153b5955928e83974","target":"record","created_at":"2026-05-17T23:39:10Z","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":"893ca7fde587799ed9ab6dfd4b926f0f30982442fd7463af5d4e823bb8b8b03d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:11:47Z","title_canon_sha256":"a2702a0981d81ef7aba76c0ab528ca84d7fb0a296e5f54e6572af9574ed46350"},"schema_version":"1.0","source":{"id":"2605.14267","kind":"arxiv","version":1}},"canonical_sha256":"3525bf22d8d2b258abe8676285435ca91eb9bf3b8527a7dad44a46a192ac91d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3525bf22d8d2b258abe8676285435ca91eb9bf3b8527a7dad44a46a192ac91d5","first_computed_at":"2026-05-17T23:39:10.430640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.430640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ouEfMJuV7ZRmHFw9gKy4TIM8aRV7FrJKGoxkONJ9JW50CJAy2eskXwT3kcPqQylRS8Vz9ginmO2WCyTwrbVeAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.431108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bc606b37d817b455e517868d011182e2cc0d290ad34b94153b5955928e83974","sha256:5233ba3a0b1b677f8cdd9c306b1ecca464e5a1df7a51f8b682d8ff70de2e1580"],"state_sha256":"a0c26f44cd2a721eadf066cfff845b9318e65e5892f3d32662b049829a36a8c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"148JLTJ+E7mt8cqdr699M4IVb3II/qzM4Q402bJNAuZirli1v/vDWbCvcDfVcSR1L0nq6Lts3GL/Z9Pd7F9nCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:28:25.379616Z","bundle_sha256":"0458024986f34f3b19440aa011cf58f2d310f0b4241ce79e6d3834396f1c198b"}}