{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:73KEXLBFN53ETFZIBBRIIAQXKY","short_pith_number":"pith:73KEXLBF","canonical_record":{"source":{"id":"2506.02986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T15:24:54Z","cross_cats_sorted":[],"title_canon_sha256":"cbce2d64e1c2f11cf50da5908b480db52ce4bfc9fe7930256754317b47e93209","abstract_canon_sha256":"055ba6ebcf4492fe64da645aceb848e87b19357031603dd1a1f90db21843f599"},"schema_version":"1.0"},"canonical_sha256":"fed44bac256f7649972808628402175604d1368049c4b2398e6a5b18627e2bfb","source":{"kind":"arxiv","id":"2506.02986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02986","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02986v1","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02986","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"73KEXLBFN53E","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"73KEXLBFN53ETFZI","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"73KEXLBF","created_at":"2026-07-05T11:15:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:73KEXLBFN53ETFZIBBRIIAQXKY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T15:24:54Z","cross_cats_sorted":[],"title_canon_sha256":"cbce2d64e1c2f11cf50da5908b480db52ce4bfc9fe7930256754317b47e93209","abstract_canon_sha256":"055ba6ebcf4492fe64da645aceb848e87b19357031603dd1a1f90db21843f599"},"schema_version":"1.0"},"canonical_sha256":"fed44bac256f7649972808628402175604d1368049c4b2398e6a5b18627e2bfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:12.954365Z","signature_b64":"AFWVY6TcP4KNHOtiYR6bUsrUnrPOGf7SjJd3reV9QgtgGJVJ3G74TABGcs0Ut6clMHlOWVwcFTfv6nx721u+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed44bac256f7649972808628402175604d1368049c4b2398e6a5b18627e2bfb","last_reissued_at":"2026-07-05T11:15:12.953951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:12.953951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02986","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":"2026-07-05T11:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZ8mJro2aXq4AkdCagsQ3GGtQnao+3CjzVue2UT3QBDXhWpWahhqR/OAwtK8nbdU7fR1WasWwDwjusE3Gv8xAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:50:39.594878Z"},"content_sha256":"c640331b95e3dd91005ea0a2d81533acc8b995eb8de87977da17ccc911a81331","schema_version":"1.0","event_id":"sha256:c640331b95e3dd91005ea0a2d81533acc8b995eb8de87977da17ccc911a81331"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:73KEXLBFN53ETFZIBBRIIAQXKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Regularization of the Deep Inverse Prior Trained with Inertia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jalal Fadil, Nathan Buskulic, Yvain Qu\\'eau","submitted_at":"2025-06-03T15:24:54Z","abstract_excerpt":"Solving inverse problems with neural networks benefits from very few theoretical guarantees when it comes to the recovery guarantees. We provide in this work convergence and recovery guarantees for self-supervised neural networks applied to inverse problems, such as Deep Image/Inverse Prior, and trained with inertia featuring both viscous and geometric Hessian-driven dampings. We study both the continuous-time case, i.e., the trajectory of a dynamical system, and the discrete case leading to an inertial algorithm with an adaptive step-size. We show in the continuous-time case that the network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02986","kind":"arxiv","version":1},"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/2506.02986/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+ujZIdW7Hn90pbW6vRiOs0hx7w5go540r3yhONrM0T0+MZ2LzhSj/EmvhBoB+5itAWXdMRIwhRceQc8jBwJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:50:39.595493Z"},"content_sha256":"fa227172bcab559b49aefacaa112bbb15e954495a5a7305fc5387094684473d6","schema_version":"1.0","event_id":"sha256:fa227172bcab559b49aefacaa112bbb15e954495a5a7305fc5387094684473d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73KEXLBFN53ETFZIBBRIIAQXKY/bundle.json","state_url":"https://pith.science/pith/73KEXLBFN53ETFZIBBRIIAQXKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73KEXLBFN53ETFZIBBRIIAQXKY/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":"2026-08-08T05:50:39Z","links":{"resolver":"https://pith.science/pith/73KEXLBFN53ETFZIBBRIIAQXKY","bundle":"https://pith.science/pith/73KEXLBFN53ETFZIBBRIIAQXKY/bundle.json","state":"https://pith.science/pith/73KEXLBFN53ETFZIBBRIIAQXKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73KEXLBFN53ETFZIBBRIIAQXKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:73KEXLBFN53ETFZIBBRIIAQXKY","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":"055ba6ebcf4492fe64da645aceb848e87b19357031603dd1a1f90db21843f599","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T15:24:54Z","title_canon_sha256":"cbce2d64e1c2f11cf50da5908b480db52ce4bfc9fe7930256754317b47e93209"},"schema_version":"1.0","source":{"id":"2506.02986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02986","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02986v1","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02986","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"73KEXLBFN53E","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"73KEXLBFN53ETFZI","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"73KEXLBF","created_at":"2026-07-05T11:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:fa227172bcab559b49aefacaa112bbb15e954495a5a7305fc5387094684473d6","target":"graph","created_at":"2026-07-05T11:15:12Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.02986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving inverse problems with neural networks benefits from very few theoretical guarantees when it comes to the recovery guarantees. We provide in this work convergence and recovery guarantees for self-supervised neural networks applied to inverse problems, such as Deep Image/Inverse Prior, and trained with inertia featuring both viscous and geometric Hessian-driven dampings. We study both the continuous-time case, i.e., the trajectory of a dynamical system, and the discrete case leading to an inertial algorithm with an adaptive step-size. We show in the continuous-time case that the network ","authors_text":"Jalal Fadil, Nathan Buskulic, Yvain Qu\\'eau","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T15:24:54Z","title":"Implicit Regularization of the Deep Inverse Prior Trained with Inertia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02986","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c640331b95e3dd91005ea0a2d81533acc8b995eb8de87977da17ccc911a81331","target":"record","created_at":"2026-07-05T11:15:12Z","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":"055ba6ebcf4492fe64da645aceb848e87b19357031603dd1a1f90db21843f599","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T15:24:54Z","title_canon_sha256":"cbce2d64e1c2f11cf50da5908b480db52ce4bfc9fe7930256754317b47e93209"},"schema_version":"1.0","source":{"id":"2506.02986","kind":"arxiv","version":1}},"canonical_sha256":"fed44bac256f7649972808628402175604d1368049c4b2398e6a5b18627e2bfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fed44bac256f7649972808628402175604d1368049c4b2398e6a5b18627e2bfb","first_computed_at":"2026-07-05T11:15:12.953951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:12.953951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AFWVY6TcP4KNHOtiYR6bUsrUnrPOGf7SjJd3reV9QgtgGJVJ3G74TABGcs0Ut6clMHlOWVwcFTfv6nx721u+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:12.954365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c640331b95e3dd91005ea0a2d81533acc8b995eb8de87977da17ccc911a81331","sha256:fa227172bcab559b49aefacaa112bbb15e954495a5a7305fc5387094684473d6"],"state_sha256":"0c5ef17f7e40e3751e56db5562c4dd1d4766bdc8ef878f7585ff7f2e877d4fa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKzZriQ9gVuYFcUqEA/eiGyNzkzndjmcTfhCjfK4x3IdgqM+ZsRWCNnXsvTgOK9KVi3zFOc6voos75GG9RURBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:50:39.600907Z","bundle_sha256":"399614cd969196ab2b14a03c26f278b2f3706b2c57696e183acb3c86b95f7c1e"}}