{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:K6XT4WYQP4J4P5DLBTVHGRNUGA","short_pith_number":"pith:K6XT4WYQ","canonical_record":{"source":{"id":"2605.08832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T09:37:34Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"353a75ed7de612672edcc5d4a591f4cbc97ce645b76f045ce81297476686e94b","abstract_canon_sha256":"c58902e967c667fbf9c0d613b39d792f646839dcf5779d4eb7e84ace7dcf8aac"},"schema_version":"1.0"},"canonical_sha256":"57af3e5b107f13c7f46b0cea7345b4302482849aff3b077c685ca54fe8dc7b73","source":{"kind":"arxiv","id":"2605.08832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08832","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08832v2","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08832","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"K6XT4WYQP4J4","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"K6XT4WYQP4J4P5DL","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"K6XT4WYQ","created_at":"2026-05-29T01:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:K6XT4WYQP4J4P5DLBTVHGRNUGA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T09:37:34Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"353a75ed7de612672edcc5d4a591f4cbc97ce645b76f045ce81297476686e94b","abstract_canon_sha256":"c58902e967c667fbf9c0d613b39d792f646839dcf5779d4eb7e84ace7dcf8aac"},"schema_version":"1.0"},"canonical_sha256":"57af3e5b107f13c7f46b0cea7345b4302482849aff3b077c685ca54fe8dc7b73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:12.261027Z","signature_b64":"2qKr/06M5ujyjCyq/8PQXgxbvGws+I8IqRqQqcdqDrg+3uggsmjBRSOoY7YvSTwX8aFg8T/LHFESBGMobaxTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57af3e5b107f13c7f46b0cea7345b4302482849aff3b077c685ca54fe8dc7b73","last_reissued_at":"2026-05-29T01:05:12.260114Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:12.260114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3NibURZZ9hVONvZzgbE+JRLqo+Kjb+89C+ZHwWuZ3kpCVxfKieW7Opc+bxH+UPjWA2wqc8YeNjKLKd/54G5LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:57:09.781076Z"},"content_sha256":"9fb98fff5afed8ec4593635b379ead0a0ebadbb61b320f03c5aead58622f0679","schema_version":"1.0","event_id":"sha256:9fb98fff5afed8ec4593635b379ead0a0ebadbb61b320f03c5aead58622f0679"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:K6XT4WYQP4J4P5DLBTVHGRNUGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inpainting physics: self-supervised learning for context-driven fluid simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time.","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Benedikt Wiestler, Daniel Rueckert, Jonas Weidner, Julian Suk, Yeray Martin-Ruisanchez","submitted_at":"2026-05-09T09:37:34Z","abstract_excerpt":"Neural surrogate models for computational fluid dynamics (CFD) are typically trained as forward operators that map explicit problem specifications, such as geometry and boundary conditions, to solution fields. This ties the model to the conditioning variables seen during training and limits reuse under boundary-condition shifts or local geometry changes. We propose to reformulate steady CFD inference as an inpainting problem: instead of training on explicit boundary conditions, we learn a self-supervised prior over velocity fields and impose boundary constraints only during inference by fixing"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our method reconstructs full velocity fields from sparse boundary context, outperforms supervised neural surrogates under boundary-condition and dataset shift and enables local geometry editing by reusing unchanged simulation context","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that a self-supervised prior learned over velocity fields without explicit boundary conditions during training will accurately and stably incorporate arbitrary new boundary constraints and local geometry changes at inference time on unseen data","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1747cf7ad2e6ac40de25346565fd4affe7437d7e26f914ca10e09329edaf4a3d"},"source":{"id":"2605.08832","kind":"arxiv","version":2},"verdict":{"id":"45626206-0b9e-43da-b128-74fbbc2f04f1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:35:47.019800Z","strongest_claim":"our method reconstructs full velocity fields from sparse boundary context, outperforms supervised neural surrogates under boundary-condition and dataset shift and enables local geometry editing by reusing unchanged simulation context","one_line_summary":"Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that a self-supervised prior learned over velocity fields without explicit boundary conditions during training will accurately and stably incorporate arbitrary new boundary constraints and local geometry changes at inference time on unseen data","pith_extraction_headline":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08832/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T08:42:02.025626Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:59.976075Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:21.827988Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:47:58.608956Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"26f356c5900fe8f0ef677760770c7b10908453ce9e83afaa4881cbacdfe67964"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46d00376238247c652b4c0da0c2fa3fda594ec9198c422c170e0b653b0ee0603"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"45626206-0b9e-43da-b128-74fbbc2f04f1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xlrqobAXyGnmMO2oyxCW+fC7u+x08FX5Bz+7tZ2RSOLfo8Bd+fEV2XOguWNZaiRtwTOz/r/rNWaa5DCwTzgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:57:09.782427Z"},"content_sha256":"e656d82bd07a4d81d1e48cefeb5bf6eab39c54ded7d070b57b59b4e73c6099ef","schema_version":"1.0","event_id":"sha256:e656d82bd07a4d81d1e48cefeb5bf6eab39c54ded7d070b57b59b4e73c6099ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/bundle.json","state_url":"https://pith.science/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/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":"2026-06-10T09:57:09Z","links":{"resolver":"https://pith.science/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA","bundle":"https://pith.science/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/bundle.json","state":"https://pith.science/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6XT4WYQP4J4P5DLBTVHGRNUGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K6XT4WYQP4J4P5DLBTVHGRNUGA","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":"c58902e967c667fbf9c0d613b39d792f646839dcf5779d4eb7e84ace7dcf8aac","cross_cats_sorted":["physics.flu-dyn"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T09:37:34Z","title_canon_sha256":"353a75ed7de612672edcc5d4a591f4cbc97ce645b76f045ce81297476686e94b"},"schema_version":"1.0","source":{"id":"2605.08832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08832","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08832v2","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08832","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"K6XT4WYQP4J4","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"K6XT4WYQP4J4P5DL","created_at":"2026-05-29T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"K6XT4WYQ","created_at":"2026-05-29T01:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:e656d82bd07a4d81d1e48cefeb5bf6eab39c54ded7d070b57b59b4e73c6099ef","target":"graph","created_at":"2026-05-29T01:05:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our method reconstructs full velocity fields from sparse boundary context, outperforms supervised neural surrogates under boundary-condition and dataset shift and enables local geometry editing by reusing unchanged simulation context"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"that a self-supervised prior learned over velocity fields without explicit boundary conditions during training will accurately and stably incorporate arbitrary new boundary constraints and local geometry changes at inference time on unseen data"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time."}],"snapshot_sha256":"1747cf7ad2e6ac40de25346565fd4affe7437d7e26f914ca10e09329edaf4a3d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46d00376238247c652b4c0da0c2fa3fda594ec9198c422c170e0b653b0ee0603"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T08:42:02.025626Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:59.976075Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:21.827988Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T10:47:58.608956Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08832/integrity.json","findings":[],"snapshot_sha256":"26f356c5900fe8f0ef677760770c7b10908453ce9e83afaa4881cbacdfe67964","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural surrogate models for computational fluid dynamics (CFD) are typically trained as forward operators that map explicit problem specifications, such as geometry and boundary conditions, to solution fields. This ties the model to the conditioning variables seen during training and limits reuse under boundary-condition shifts or local geometry changes. We propose to reformulate steady CFD inference as an inpainting problem: instead of training on explicit boundary conditions, we learn a self-supervised prior over velocity fields and impose boundary constraints only during inference by fixing","authors_text":"Benedikt Wiestler, Daniel Rueckert, Jonas Weidner, Julian Suk, Yeray Martin-Ruisanchez","cross_cats":["physics.flu-dyn"],"headline":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T09:37:34Z","title":"Inpainting physics: self-supervised learning for context-driven fluid simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08832","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:35:47.019800Z","id":"45626206-0b9e-43da-b128-74fbbc2f04f1","model_set":{"reader":"grok-4.3"},"one_line_summary":"Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Reformulating steady fluid simulation as inpainting lets a self-supervised prior over velocity fields adapt to new boundary conditions at inference time.","strongest_claim":"our method reconstructs full velocity fields from sparse boundary context, outperforms supervised neural surrogates under boundary-condition and dataset shift and enables local geometry editing by reusing unchanged simulation context","weakest_assumption":"that a self-supervised prior learned over velocity fields without explicit boundary conditions during training will accurately and stably incorporate arbitrary new boundary constraints and local geometry changes at inference time on unseen data"}},"verdict_id":"45626206-0b9e-43da-b128-74fbbc2f04f1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9fb98fff5afed8ec4593635b379ead0a0ebadbb61b320f03c5aead58622f0679","target":"record","created_at":"2026-05-29T01:05:12Z","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":"c58902e967c667fbf9c0d613b39d792f646839dcf5779d4eb7e84ace7dcf8aac","cross_cats_sorted":["physics.flu-dyn"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T09:37:34Z","title_canon_sha256":"353a75ed7de612672edcc5d4a591f4cbc97ce645b76f045ce81297476686e94b"},"schema_version":"1.0","source":{"id":"2605.08832","kind":"arxiv","version":2}},"canonical_sha256":"57af3e5b107f13c7f46b0cea7345b4302482849aff3b077c685ca54fe8dc7b73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57af3e5b107f13c7f46b0cea7345b4302482849aff3b077c685ca54fe8dc7b73","first_computed_at":"2026-05-29T01:05:12.260114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:12.260114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2qKr/06M5ujyjCyq/8PQXgxbvGws+I8IqRqQqcdqDrg+3uggsmjBRSOoY7YvSTwX8aFg8T/LHFESBGMobaxTCA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:12.261027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fb98fff5afed8ec4593635b379ead0a0ebadbb61b320f03c5aead58622f0679","sha256:e656d82bd07a4d81d1e48cefeb5bf6eab39c54ded7d070b57b59b4e73c6099ef"],"state_sha256":"955a54498d9daa85c1a5ca540cd0723574f92488f0efac9977aad1ada59927fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wWOQ/HXFTwLkZQY5aJ5HYZXv5h8nYGIbT3xSatqFcdjX2zwN1twnosDhz9y1ESum89BAgGDGcNplgMJlZiZMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:57:09.788108Z","bundle_sha256":"07b8ff9e27d4091472c6043952d40e231b6f7604e28bdc952b1213fee0ef025b"}}