{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SLILGLWMSAL53M534BBNS5JQOU","short_pith_number":"pith:SLILGLWM","canonical_record":{"source":{"id":"2510.00929","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"b47507b86a48c217350bef7a8a10e640022fd01d46646e225ed12000c462a074","abstract_canon_sha256":"e494577b742c2febd16be3d59c16d3db619eca56ff57a57a2eaf25c83200b810"},"schema_version":"1.0"},"canonical_sha256":"92d0b32ecc9017ddb3bbe042d975307507e83be7f67bfc308f0b35f79f9d2a98","source":{"kind":"arxiv","id":"2510.00929","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00929","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00929v6","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00929","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"SLILGLWMSAL5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SLILGLWMSAL53M53","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SLILGLWM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SLILGLWMSAL53M534BBNS5JQOU","target":"record","payload":{"canonical_record":{"source":{"id":"2510.00929","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"b47507b86a48c217350bef7a8a10e640022fd01d46646e225ed12000c462a074","abstract_canon_sha256":"e494577b742c2febd16be3d59c16d3db619eca56ff57a57a2eaf25c83200b810"},"schema_version":"1.0"},"canonical_sha256":"92d0b32ecc9017ddb3bbe042d975307507e83be7f67bfc308f0b35f79f9d2a98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:12.146177Z","signature_b64":"ztYCUZCi9h811OA8XNGRMQIKUJPBqr8aPoply6z6B/qQLY9u2Sf3edtJ5Q+76Dxmc3LlCq7quUC9W4ifneBZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92d0b32ecc9017ddb3bbe042d975307507e83be7f67bfc308f0b35f79f9d2a98","last_reissued_at":"2026-05-18T03:10:12.145500Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:12.145500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.00929","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUG3GBVBTA6Z7c4y1zMGo8I+F/iiYxHAqjBcWxGH30rYbqYl15NS6cd2ingtFtRjJlnhV/CQiHs2vQybQj6IBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:16:39.967445Z"},"content_sha256":"4a99ecaaf3f4c60786292c5b6b57e0f0def739593784ef366140df223c9e4954","schema_version":"1.0","event_id":"sha256:4a99ecaaf3f4c60786292c5b6b57e0f0def739593784ef366140df223c9e4954"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SLILGLWMSAL53M534BBNS5JQOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivariant Splitting: Self-supervised learning from incomplete data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J\\'er\\'emy Scanvic, Juli\\'an Tachella, Patrice Abry, Quentin Barth\\'elemy, Victor Sechaud","submitted_at":"2025-10-01T14:08:17Z","abstract_excerpt":"Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equivariance in the context of reconstruction networks, and show that the combination of self-supervised sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00929","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PR52X3+NstOdt99XVu9YrRjm+UE7I6Ah2O5QCAQHcGIDtV75NkL3wzKXos0+hF3OoJA4V4hAgdaGEf1z3oLLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:16:39.967791Z"},"content_sha256":"97ff8adb2ce4f688d7155f83b3959136886a8a066485cb54197dd68b35cdef61","schema_version":"1.0","event_id":"sha256:97ff8adb2ce4f688d7155f83b3959136886a8a066485cb54197dd68b35cdef61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLILGLWMSAL53M534BBNS5JQOU/bundle.json","state_url":"https://pith.science/pith/SLILGLWMSAL53M534BBNS5JQOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLILGLWMSAL53M534BBNS5JQOU/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":"2026-05-21T06:16:39Z","links":{"resolver":"https://pith.science/pith/SLILGLWMSAL53M534BBNS5JQOU","bundle":"https://pith.science/pith/SLILGLWMSAL53M534BBNS5JQOU/bundle.json","state":"https://pith.science/pith/SLILGLWMSAL53M534BBNS5JQOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLILGLWMSAL53M534BBNS5JQOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SLILGLWMSAL53M534BBNS5JQOU","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":"e494577b742c2febd16be3d59c16d3db619eca56ff57a57a2eaf25c83200b810","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:08:17Z","title_canon_sha256":"b47507b86a48c217350bef7a8a10e640022fd01d46646e225ed12000c462a074"},"schema_version":"1.0","source":{"id":"2510.00929","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00929","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00929v6","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00929","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"SLILGLWMSAL5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SLILGLWMSAL53M53","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SLILGLWM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:97ff8adb2ce4f688d7155f83b3959136886a8a066485cb54197dd68b35cdef61","target":"graph","created_at":"2026-05-18T03:10:12Z","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"},"paper":{"abstract_excerpt":"Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equivariance in the context of reconstruction networks, and show that the combination of self-supervised sp","authors_text":"J\\'er\\'emy Scanvic, Juli\\'an Tachella, Patrice Abry, Quentin Barth\\'elemy, Victor Sechaud","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:08:17Z","title":"Equivariant Splitting: Self-supervised learning from incomplete data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00929","kind":"arxiv","version":6},"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":"sha256:4a99ecaaf3f4c60786292c5b6b57e0f0def739593784ef366140df223c9e4954","target":"record","created_at":"2026-05-18T03:10:12Z","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":"e494577b742c2febd16be3d59c16d3db619eca56ff57a57a2eaf25c83200b810","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:08:17Z","title_canon_sha256":"b47507b86a48c217350bef7a8a10e640022fd01d46646e225ed12000c462a074"},"schema_version":"1.0","source":{"id":"2510.00929","kind":"arxiv","version":6}},"canonical_sha256":"92d0b32ecc9017ddb3bbe042d975307507e83be7f67bfc308f0b35f79f9d2a98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92d0b32ecc9017ddb3bbe042d975307507e83be7f67bfc308f0b35f79f9d2a98","first_computed_at":"2026-05-18T03:10:12.145500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:12.145500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ztYCUZCi9h811OA8XNGRMQIKUJPBqr8aPoply6z6B/qQLY9u2Sf3edtJ5Q+76Dxmc3LlCq7quUC9W4ifneBZDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:12.146177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.00929","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a99ecaaf3f4c60786292c5b6b57e0f0def739593784ef366140df223c9e4954","sha256:97ff8adb2ce4f688d7155f83b3959136886a8a066485cb54197dd68b35cdef61"],"state_sha256":"580acc7835a72300cf60c5bc9457ee1d65c07c536e57bd784b12edd7990798eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVSRXpnG12qT3fXi/Os8W/xtg0a5qlpUHsycwO+ON4/NDuRoHs+rQshrQwg5jxe5VyvnN3YOxzGs+mY4XpZsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T06:16:39.969795Z","bundle_sha256":"f9e031f96317074be8dc76c1d137fe5030a0210ecd5f10e3d5c4a5c17bb919b1"}}