{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:65JLQ6WY7W2X4RT4YD7QJKHQ74","short_pith_number":"pith:65JLQ6WY","schema_version":"1.0","canonical_sha256":"f752b87ad8fdb57e467cc0ff04a8f0ff36538d97c06bcaa6aa0a65e53b2c78c4","source":{"kind":"arxiv","id":"2512.16357","version":3},"attestation_state":"computed","paper":{"title":"GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peng Wu, Qingsen Yan, Tao Hu, Wei Dong, Weiyu Zhou, Yanjie Tu, Yanning Zhang","submitted_at":"2025-12-18T09:50:25Z","abstract_excerpt":"Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying LDMs to HDR remains challenging due to: (1) limited dynamic-range representation caused by 8-bit latent compression, (2) high inference cost from multi-step denoising, and (3) content hallucination inherent to their generative nature. To address these challenges, we introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconst"},"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":"2512.16357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T09:50:25Z","cross_cats_sorted":[],"title_canon_sha256":"00931dda7e8e90b599c15bd1549f171274aac02b5d2d8e98af9bc30616c96fe2","abstract_canon_sha256":"d0a4a19ccce83b353021b8d298921d1382a752536e7ac8e44fb7ba60db0e3fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:31.842961Z","signature_b64":"VG5JvV5BhRsmSMqEju5ft6g61s6ld7Gd/+8bfpiFvf3Nz98rYIVTQBo2bmLiwKg2O6S5ecMF+j3eGWehErJmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f752b87ad8fdb57e467cc0ff04a8f0ff36538d97c06bcaa6aa0a65e53b2c78c4","last_reissued_at":"2026-07-07T02:18:31.842024Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:31.842024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peng Wu, Qingsen Yan, Tao Hu, Wei Dong, Weiyu Zhou, Yanjie Tu, Yanning Zhang","submitted_at":"2025-12-18T09:50:25Z","abstract_excerpt":"Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying LDMs to HDR remains challenging due to: (1) limited dynamic-range representation caused by 8-bit latent compression, (2) high inference cost from multi-step denoising, and (3) content hallucination inherent to their generative nature. To address these challenges, we introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.16357","kind":"arxiv","version":3},"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/2512.16357/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":"2512.16357","created_at":"2026-07-07T02:18:31.842135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.16357v3","created_at":"2026-07-07T02:18:31.842135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16357","created_at":"2026-07-07T02:18:31.842135+00:00"},{"alias_kind":"pith_short_12","alias_value":"65JLQ6WY7W2X","created_at":"2026-07-07T02:18:31.842135+00:00"},{"alias_kind":"pith_short_16","alias_value":"65JLQ6WY7W2X4RT4","created_at":"2026-07-07T02:18:31.842135+00:00"},{"alias_kind":"pith_short_8","alias_value":"65JLQ6WY","created_at":"2026-07-07T02:18:31.842135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05626","citing_title":"Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74","json":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74.json","graph_json":"https://pith.science/api/pith-number/65JLQ6WY7W2X4RT4YD7QJKHQ74/graph.json","events_json":"https://pith.science/api/pith-number/65JLQ6WY7W2X4RT4YD7QJKHQ74/events.json","paper":"https://pith.science/paper/65JLQ6WY"},"agent_actions":{"view_html":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74","download_json":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74.json","view_paper":"https://pith.science/paper/65JLQ6WY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.16357&json=true","fetch_graph":"https://pith.science/api/pith-number/65JLQ6WY7W2X4RT4YD7QJKHQ74/graph.json","fetch_events":"https://pith.science/api/pith-number/65JLQ6WY7W2X4RT4YD7QJKHQ74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74/action/storage_attestation","attest_author":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74/action/author_attestation","sign_citation":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74/action/citation_signature","submit_replication":"https://pith.science/pith/65JLQ6WY7W2X4RT4YD7QJKHQ74/action/replication_record"}},"created_at":"2026-07-07T02:18:31.842135+00:00","updated_at":"2026-07-07T02:18:31.842135+00:00"}