{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:55X6Q3SYDRARDQZEO7GTRGCD6Q","short_pith_number":"pith:55X6Q3SY","schema_version":"1.0","canonical_sha256":"ef6fe86e581c4111c32477cd389843f41eb3c351b5a1f4332bee7d231267e71b","source":{"kind":"arxiv","id":"2510.03352","version":3},"attestation_state":"computed","paper":{"title":"Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dileep Kalathil, Jean-Francois Chamberland, Krishna Narayanan, Mahdi Farahbakhsh, Vishnu Teja Kunde","submitted_at":"2025-10-02T20:16:00Z","abstract_excerpt":"Diffusion models have been used as priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruction quality, especially in severely ill-posed settings. In this work, we propose a novel framework that incorporates side information into existing diffusion-based inverse problem solvers via inference-time search, in a plug-and-play, training-free manner. Through extensive experiments across a range of inverse problems, including inpainting, super-resolution, and several deblurring tasks, and across multiple diffus"},"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":"2510.03352","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:16:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"389c051e926ad9c881fdc5009e17ec46d7264aff59e9b14375ee93e66af9e7bf","abstract_canon_sha256":"be322e0bec693eccc7c4e770343ec45bf1da73998b40c6df38940a2e1c2609d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:51.850612Z","signature_b64":"jj0GwEGwPWZ2l88lM4bCn/SP2R5EI3jsFKcTPnYuo8TlplpZ4T5G6OiO0EOVbtrWlEF7b55BoHDFJjuBD5i9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6fe86e581c4111c32477cd389843f41eb3c351b5a1f4332bee7d231267e71b","last_reissued_at":"2026-05-27T01:04:51.849717Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:51.849717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dileep Kalathil, Jean-Francois Chamberland, Krishna Narayanan, Mahdi Farahbakhsh, Vishnu Teja Kunde","submitted_at":"2025-10-02T20:16:00Z","abstract_excerpt":"Diffusion models have been used as priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruction quality, especially in severely ill-posed settings. In this work, we propose a novel framework that incorporates side information into existing diffusion-based inverse problem solvers via inference-time search, in a plug-and-play, training-free manner. Through extensive experiments across a range of inverse problems, including inpainting, super-resolution, and several deblurring tasks, and across multiple diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03352","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/2510.03352/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":"2510.03352","created_at":"2026-05-27T01:04:51.849838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03352v3","created_at":"2026-05-27T01:04:51.849838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03352","created_at":"2026-05-27T01:04:51.849838+00:00"},{"alias_kind":"pith_short_12","alias_value":"55X6Q3SYDRAR","created_at":"2026-05-27T01:04:51.849838+00:00"},{"alias_kind":"pith_short_16","alias_value":"55X6Q3SYDRARDQZE","created_at":"2026-05-27T01:04:51.849838+00:00"},{"alias_kind":"pith_short_8","alias_value":"55X6Q3SY","created_at":"2026-05-27T01:04:51.849838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.23532","citing_title":"Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q","json":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q.json","graph_json":"https://pith.science/api/pith-number/55X6Q3SYDRARDQZEO7GTRGCD6Q/graph.json","events_json":"https://pith.science/api/pith-number/55X6Q3SYDRARDQZEO7GTRGCD6Q/events.json","paper":"https://pith.science/paper/55X6Q3SY"},"agent_actions":{"view_html":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q","download_json":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q.json","view_paper":"https://pith.science/paper/55X6Q3SY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03352&json=true","fetch_graph":"https://pith.science/api/pith-number/55X6Q3SYDRARDQZEO7GTRGCD6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/55X6Q3SYDRARDQZEO7GTRGCD6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q/action/storage_attestation","attest_author":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q/action/author_attestation","sign_citation":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q/action/citation_signature","submit_replication":"https://pith.science/pith/55X6Q3SYDRARDQZEO7GTRGCD6Q/action/replication_record"}},"created_at":"2026-05-27T01:04:51.849838+00:00","updated_at":"2026-05-27T01:04:51.849838+00:00"}