{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KPHL7WYPLSRXYR7BFASDL5ONVJ","short_pith_number":"pith:KPHL7WYP","canonical_record":{"source":{"id":"2605.14045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T19:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"c5d87fceef56652ad4bfd680edd7521c4b5995b32b4cf197c3c77144ae2cab30","abstract_canon_sha256":"a128e7584c2d47dd93fa9b135ea35bada41ab99ebb52b7e254e9e227fd6ad2c2"},"schema_version":"1.0"},"canonical_sha256":"53cebfdb0f5ca37c47e1282435f5cdaa786818917b8a2c5b6c981be4e5f20276","source":{"kind":"arxiv","id":"2605.14045","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14045","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14045v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14045","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"KPHL7WYPLSRX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KPHL7WYPLSRXYR7B","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KPHL7WYP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KPHL7WYPLSRXYR7BFASDL5ONVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T19:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"c5d87fceef56652ad4bfd680edd7521c4b5995b32b4cf197c3c77144ae2cab30","abstract_canon_sha256":"a128e7584c2d47dd93fa9b135ea35bada41ab99ebb52b7e254e9e227fd6ad2c2"},"schema_version":"1.0"},"canonical_sha256":"53cebfdb0f5ca37c47e1282435f5cdaa786818917b8a2c5b6c981be4e5f20276","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:12.703180Z","signature_b64":"OntnjIuRtX82V/+BnNQRDOWos2WCW1Ugqkg91Dk7uqoxYhp05uB8dC4y7uQqfXo4MklSuC6sIQ23ZMfOcfIqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53cebfdb0f5ca37c47e1282435f5cdaa786818917b8a2c5b6c981be4e5f20276","last_reissued_at":"2026-05-17T23:39:12.702537Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:12.702537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14045","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":"2026-05-17T23:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8YN/qcgkf3cRNd6f6TrQ6DIn84zKocBBzm3RmLq7qpllnpmlHoh4vd5vyj16Rsozgc3kp9IOjZVYvpHke0hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:22:03.659751Z"},"content_sha256":"032df3881066aa8bc927a06b5244ceab4d65769702c35f1842516844a0a37996","schema_version":"1.0","event_id":"sha256:032df3881066aa8bc927a06b5244ceab4d65769702c35f1842516844a0a37996"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KPHL7WYPLSRXYR7BFASDL5ONVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Guanhua Zhao, Han Zhou, Jun Chen, Shahab Asoodeh, Terry Ji, Wei Dong, Xiaohong Liu, Yulun Zhang","submitted_at":"2026-05-13T19:07:14Z","abstract_excerpt":"Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth results. We propose PVRF, a unified framework that integrates zero-shot soft weather perceptions with velocity-constrained rectified-flow refinement. PVRF introduces an AWR-specific question answering module (AWR-QA) that uses frozen vision--language models (VLMs) to estimate soft probabilities of weather types and low-level attribute scores. These perceptions condition restoration networks via attribute-modulated norma"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Zero-shot soft weather perceptions produced by frozen VLMs via the AWR-QA module are sufficiently accurate and informative to condition the restoration networks effectively through AMN and WWA.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9b776bbb19dd19ca86839ad690679e00b9dec62a88a17ee530cbe98526d7a103"},"source":{"id":"2605.14045","kind":"arxiv","version":1},"verdict":{"id":"6cc8dc28-3b0d-4924-86f6-2a7b1e8b2e6b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:41:19.488862Z","strongest_claim":"PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations.","one_line_summary":"PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Zero-shot soft weather perceptions produced by frozen VLMs via the AWR-QA module are sufficiently accurate and informative to condition the restoration networks effectively through AMN and WWA.","pith_extraction_headline":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations."},"references":{"count":49,"sample":[{"doi":"","year":2018,"title":"The perception-distortion tradeoff","work_id":"8f7c1692-5452-4dc1-97b6-56c11153d5f8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Unirestore: Unified perceptual and task-oriented image restoration model using diffusion prior","work_id":"acbdda1c-5bf7-432a-bff7-a505cc3f3e73","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Simple baselines for image restoration","work_id":"0e714e9d-2b6b-4cda-ae2e-3c9d63bb1d5d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss","work_id":"ff5d9456-46bf-4231-839e-d2b356bf1c0a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Bio-inspired image restoration","work_id":"f2b9bd5f-9bf0-42f2-a338-e751fc8c71e5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":49,"snapshot_sha256":"e33c2f6542eb037ff4286df1eeb0f68be18962cfbe54fdb3af14c5733bc49bae","internal_anchors":1},"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":"6cc8dc28-3b0d-4924-86f6-2a7b1e8b2e6b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UcwYV/laY+hoPhZe3V77/5qi7zJQDaHTdYEWk/dYOlr2KtBkexRBK1Ypv0FhLEOTQ7Zd4H8ad4zvLZr3BT1WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:22:03.660873Z"},"content_sha256":"721c6104040bd11c5991331a4079f2f273e2b8c480cd3e5d8409e578147d5b93","schema_version":"1.0","event_id":"sha256:721c6104040bd11c5991331a4079f2f273e2b8c480cd3e5d8409e578147d5b93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/bundle.json","state_url":"https://pith.science/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/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":"2026-05-19T05:22:03Z","links":{"resolver":"https://pith.science/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ","bundle":"https://pith.science/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/bundle.json","state":"https://pith.science/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPHL7WYPLSRXYR7BFASDL5ONVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPHL7WYPLSRXYR7BFASDL5ONVJ","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":"a128e7584c2d47dd93fa9b135ea35bada41ab99ebb52b7e254e9e227fd6ad2c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T19:07:14Z","title_canon_sha256":"c5d87fceef56652ad4bfd680edd7521c4b5995b32b4cf197c3c77144ae2cab30"},"schema_version":"1.0","source":{"id":"2605.14045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14045","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14045v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14045","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"KPHL7WYPLSRX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KPHL7WYPLSRXYR7B","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KPHL7WYP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:721c6104040bd11c5991331a4079f2f273e2b8c480cd3e5d8409e578147d5b93","target":"graph","created_at":"2026-05-17T23:39:12Z","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":"PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Zero-shot soft weather perceptions produced by frozen VLMs via the AWR-QA module are sufficiently accurate and informative to condition the restoration networks effectively through AMN and WWA."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations."}],"snapshot_sha256":"9b776bbb19dd19ca86839ad690679e00b9dec62a88a17ee530cbe98526d7a103"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth results. We propose PVRF, a unified framework that integrates zero-shot soft weather perceptions with velocity-constrained rectified-flow refinement. PVRF introduces an AWR-specific question answering module (AWR-QA) that uses frozen vision--language models (VLMs) to estimate soft probabilities of weather types and low-level attribute scores. These perceptions condition restoration networks via attribute-modulated norma","authors_text":"Guangtao Zhai, Guanhua Zhao, Han Zhou, Jun Chen, Shahab Asoodeh, Terry Ji, Wei Dong, Xiaohong Liu, Yulun Zhang","cross_cats":[],"headline":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T19:07:14Z","title":"PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow"},"references":{"count":49,"internal_anchors":1,"resolved_work":49,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The perception-distortion tradeoff","work_id":"8f7c1692-5452-4dc1-97b6-56c11153d5f8","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Unirestore: Unified perceptual and task-oriented image restoration model using diffusion prior","work_id":"acbdda1c-5bf7-432a-bff7-a505cc3f3e73","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Simple baselines for image restoration","work_id":"0e714e9d-2b6b-4cda-ae2e-3c9d63bb1d5d","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss","work_id":"ff5d9456-46bf-4231-839e-d2b356bf1c0a","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bio-inspired image restoration","work_id":"f2b9bd5f-9bf0-42f2-a338-e751fc8c71e5","year":2025}],"snapshot_sha256":"e33c2f6542eb037ff4286df1eeb0f68be18962cfbe54fdb3af14c5733bc49bae"},"source":{"id":"2605.14045","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:41:19.488862Z","id":"6cc8dc28-3b0d-4924-86f6-2a7b1e8b2e6b","model_set":{"reader":"grok-4.3"},"one_line_summary":"PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PVRF uses zero-shot weather perceptions from frozen vision-language models to guide a velocity-constrained rectified flow that refines restoration anchors for multiple adverse degradations.","strongest_claim":"PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations.","weakest_assumption":"Zero-shot soft weather perceptions produced by frozen VLMs via the AWR-QA module are sufficiently accurate and informative to condition the restoration networks effectively through AMN and WWA."}},"verdict_id":"6cc8dc28-3b0d-4924-86f6-2a7b1e8b2e6b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:032df3881066aa8bc927a06b5244ceab4d65769702c35f1842516844a0a37996","target":"record","created_at":"2026-05-17T23:39:12Z","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":"a128e7584c2d47dd93fa9b135ea35bada41ab99ebb52b7e254e9e227fd6ad2c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T19:07:14Z","title_canon_sha256":"c5d87fceef56652ad4bfd680edd7521c4b5995b32b4cf197c3c77144ae2cab30"},"schema_version":"1.0","source":{"id":"2605.14045","kind":"arxiv","version":1}},"canonical_sha256":"53cebfdb0f5ca37c47e1282435f5cdaa786818917b8a2c5b6c981be4e5f20276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53cebfdb0f5ca37c47e1282435f5cdaa786818917b8a2c5b6c981be4e5f20276","first_computed_at":"2026-05-17T23:39:12.702537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:12.702537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OntnjIuRtX82V/+BnNQRDOWos2WCW1Ugqkg91Dk7uqoxYhp05uB8dC4y7uQqfXo4MklSuC6sIQ23ZMfOcfIqAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:12.703180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:032df3881066aa8bc927a06b5244ceab4d65769702c35f1842516844a0a37996","sha256:721c6104040bd11c5991331a4079f2f273e2b8c480cd3e5d8409e578147d5b93"],"state_sha256":"5899fa1a62faeb896d5684091a1193346bd666ef7f21b6de33b055ede74a8104"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3cApLbEyzoG5s2Yu/WIVPvCONywnF81mpUX4sITuF/uBj3a50uTImhpJ/7QC65vjzsXZ3Fx4zeO4dNm8dXWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T05:22:03.664048Z","bundle_sha256":"48df70d6be2e3278efe82966fde072954eaa668f04db669b59d9f93d7345bf16"}}