{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I4KKES37KHTVIWXYFA2AAVOJQD","short_pith_number":"pith:I4KKES37","schema_version":"1.0","canonical_sha256":"4714a24b7f51e7545af828340055c980e5c0d89c1353898192a3e25ea087fc4c","source":{"kind":"arxiv","id":"2605.02198","version":2},"attestation_state":"computed","paper":{"title":"SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SlimDiffSR distills a diffusion model into a single-step student network that runs 200 times faster and uses 20 times fewer parameters for remote sensing super-resolution.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Wang, Wanjie Sun, Zhenyu Hu","submitted_at":"2026-05-04T03:54:54Z","abstract_excerpt":"Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution. Unlike existing single-step diffusion methods that rely on fixed timesteps, we first introduce an uncertainty-guided timestep assignment strategy to construct a stronger single-step teacher model, where reconstruction difficulty is explicitly linked to diff"},"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":"2605.02198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-04T03:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"afdafc3d8262a5924e37a6b40c2de3c2a8567232cec41a391b91b8d77bf8f8e6","abstract_canon_sha256":"294f8f4e658abc77b6346d72a10c771f0a50a5a800a04a7c114784dac7848a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:33.586308Z","signature_b64":"hkfbzoS12bRLy1buG6KHnPfOJAQQcGneKKoaJgolgoV9Jz/VywmD/oqiQkPjykntnJfCuxys58lBMllqx4YwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4714a24b7f51e7545af828340055c980e5c0d89c1353898192a3e25ea087fc4c","last_reissued_at":"2026-05-20T00:04:33.585516Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:33.585516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SlimDiffSR distills a diffusion model into a single-step student network that runs 200 times faster and uses 20 times fewer parameters for remote sensing super-resolution.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Wang, Wanjie Sun, Zhenyu Hu","submitted_at":"2026-05-04T03:54:54Z","abstract_excerpt":"Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution. Unlike existing single-step diffusion methods that rely on fixed timesteps, we first introduce an uncertainty-guided timestep assignment strategy to construct a stronger single-step teacher model, where reconstruction difficulty is explicitly linked to diff"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SlimDiffSR attains up to 200× inference acceleration and a 20× reduction in model parameters compared with multi-step diffusion models, while achieving competitive perceptual quality and clearly outperforming existing lightweight diffusion baselines in efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the uncertainty-guided timestep assignment and structured pruning with frequency- and direction-separable convolutions plus MMD distillation will preserve generative quality on remote sensing data without significant degradation or domain-specific failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SlimDiffSR uses uncertainty-guided timestep assignment and remote-sensing-tailored pruning plus MMD distillation to create a diffusion SR model with 200x faster inference and 20x fewer parameters while keeping competitive quality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SlimDiffSR distills a diffusion model into a single-step student network that runs 200 times faster and uses 20 times fewer parameters for remote sensing super-resolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2087beca08d9e242facaff1b5e42864eca39cf54123c440a02b94366ef7bf8a2"},"source":{"id":"2605.02198","kind":"arxiv","version":2},"verdict":{"id":"2e6e88ba-36bc-4871-97a5-eb8b28150a2a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T16:29:26.114377Z","strongest_claim":"SlimDiffSR attains up to 200× inference acceleration and a 20× reduction in model parameters compared with multi-step diffusion models, while achieving competitive perceptual quality and clearly outperforming existing lightweight diffusion baselines in efficiency.","one_line_summary":"SlimDiffSR uses uncertainty-guided timestep assignment and remote-sensing-tailored pruning plus MMD distillation to create a diffusion SR model with 200x faster inference and 20x fewer parameters while keeping competitive quality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the uncertainty-guided timestep assignment and structured pruning with frequency- and direction-separable convolutions plus MMD distillation will preserve generative quality on remote sensing data without significant degradation or domain-specific failure modes.","pith_extraction_headline":"SlimDiffSR distills a diffusion model into a single-step student network that runs 200 times faster and uses 20 times fewer parameters for remote sensing super-resolution."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02198/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:37:21.620924Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fbafd5c39d98f010ebf928383f81fb58aee7a19be6e02e36df7d3ae4a3f7dd0f"},"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":"2605.02198","created_at":"2026-05-20T00:04:33.585645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.02198v2","created_at":"2026-05-20T00:04:33.585645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02198","created_at":"2026-05-20T00:04:33.585645+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4KKES37KHTV","created_at":"2026-05-20T00:04:33.585645+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4KKES37KHTVIWXY","created_at":"2026-05-20T00:04:33.585645+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4KKES37","created_at":"2026-05-20T00:04:33.585645+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/I4KKES37KHTVIWXYFA2AAVOJQD","json":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD.json","graph_json":"https://pith.science/api/pith-number/I4KKES37KHTVIWXYFA2AAVOJQD/graph.json","events_json":"https://pith.science/api/pith-number/I4KKES37KHTVIWXYFA2AAVOJQD/events.json","paper":"https://pith.science/paper/I4KKES37"},"agent_actions":{"view_html":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD","download_json":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD.json","view_paper":"https://pith.science/paper/I4KKES37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.02198&json=true","fetch_graph":"https://pith.science/api/pith-number/I4KKES37KHTVIWXYFA2AAVOJQD/graph.json","fetch_events":"https://pith.science/api/pith-number/I4KKES37KHTVIWXYFA2AAVOJQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD/action/storage_attestation","attest_author":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD/action/author_attestation","sign_citation":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD/action/citation_signature","submit_replication":"https://pith.science/pith/I4KKES37KHTVIWXYFA2AAVOJQD/action/replication_record"}},"created_at":"2026-05-20T00:04:33.585645+00:00","updated_at":"2026-05-20T00:04:33.585645+00:00"}