{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2IARPAM3W54MNTCFKE7HGNWMK","short_pith_number":"pith:E2IARPAM","schema_version":"1.0","canonical_sha256":"269008bc0cddbbc636622a89f399b6629495c1e0ca3aa7c5e372497e4289dd51","source":{"kind":"arxiv","id":"2512.09806","version":2},"attestation_state":"computed","paper":{"title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gitta Kutyniok, Ines Rosellon-Inclan, Jean-Luc Starck, Jianfei Li","submitted_at":"2025-12-10T16:20:00Z","abstract_excerpt":"Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these methods may generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios. This paper introduces a framework for quantifying and characterizing hallucinated artifacts in image reconstruction models. The proposed method, termed the Conformal Hallucination Estimation Metric (CHEM), enables the identification of hallucination-prone regions in model predictions. It leverages wavelet and shearlet repres"},"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":"2512.09806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-10T16:20:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bcbb6b396d2d7427598f10c7faba7c09f6c7a0e270355c239df6c6e5705e6cad","abstract_canon_sha256":"0c15e0ce932b87a471f4fef1fcedb01379cc6db1f0d0c22f65f9858014da15d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:13.157731Z","signature_b64":"QmQ2o7mWHC3ofTJVJF6uG9sUqJPqBXi06whJ10dFksBI0JMgslE1TEzB1W8E/WjGuARKALyw0PEiSbkQNva6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"269008bc0cddbbc636622a89f399b6629495c1e0ca3aa7c5e372497e4289dd51","last_reissued_at":"2026-05-21T01:05:13.156947Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:13.156947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gitta Kutyniok, Ines Rosellon-Inclan, Jean-Luc Starck, Jianfei Li","submitted_at":"2025-12-10T16:20:00Z","abstract_excerpt":"Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these methods may generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios. This paper introduces a framework for quantifying and characterizing hallucinated artifacts in image reconstruction models. The proposed method, termed the Conformal Hallucination Estimation Metric (CHEM), enables the identification of hallucination-prone regions in model predictions. It leverages wavelet and shearlet repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.09806","kind":"arxiv","version":2},"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/2512.09806/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":"2512.09806","created_at":"2026-05-21T01:05:13.157055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.09806v2","created_at":"2026-05-21T01:05:13.157055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.09806","created_at":"2026-05-21T01:05:13.157055+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2IARPAM3W54","created_at":"2026-05-21T01:05:13.157055+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2IARPAM3W54MNTC","created_at":"2026-05-21T01:05:13.157055+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2IARPAM","created_at":"2026-05-21T01:05:13.157055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13146","citing_title":"On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK","json":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK.json","graph_json":"https://pith.science/api/pith-number/E2IARPAM3W54MNTCFKE7HGNWMK/graph.json","events_json":"https://pith.science/api/pith-number/E2IARPAM3W54MNTCFKE7HGNWMK/events.json","paper":"https://pith.science/paper/E2IARPAM"},"agent_actions":{"view_html":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK","download_json":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK.json","view_paper":"https://pith.science/paper/E2IARPAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.09806&json=true","fetch_graph":"https://pith.science/api/pith-number/E2IARPAM3W54MNTCFKE7HGNWMK/graph.json","fetch_events":"https://pith.science/api/pith-number/E2IARPAM3W54MNTCFKE7HGNWMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK/action/storage_attestation","attest_author":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK/action/author_attestation","sign_citation":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK/action/citation_signature","submit_replication":"https://pith.science/pith/E2IARPAM3W54MNTCFKE7HGNWMK/action/replication_record"}},"created_at":"2026-05-21T01:05:13.157055+00:00","updated_at":"2026-05-21T01:05:13.157055+00:00"}