{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IMLN6CJRIAUFAZNULT4ENI5DQS","short_pith_number":"pith:IMLN6CJR","canonical_record":{"source":{"id":"2605.05540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T00:41:47Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"ecd340cccd0642893ab85be5612af305bc910bd69c266ffc229f3f8638a02da0","abstract_canon_sha256":"2f6a418b0e469850555349606e8328c08aa9a251b6f6c5fcb6bdc36f8e6b54c0"},"schema_version":"1.0"},"canonical_sha256":"4316df093140285065b45cf846a3a384b888813392130da0eb269a83c405c863","source":{"kind":"arxiv","id":"2605.05540","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05540","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05540v2","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05540","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"IMLN6CJRIAUF","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"IMLN6CJRIAUFAZNU","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"IMLN6CJR","created_at":"2026-07-28T02:23:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IMLN6CJRIAUFAZNULT4ENI5DQS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.05540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T00:41:47Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"ecd340cccd0642893ab85be5612af305bc910bd69c266ffc229f3f8638a02da0","abstract_canon_sha256":"2f6a418b0e469850555349606e8328c08aa9a251b6f6c5fcb6bdc36f8e6b54c0"},"schema_version":"1.0"},"canonical_sha256":"4316df093140285065b45cf846a3a384b888813392130da0eb269a83c405c863","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:32.098172Z","signature_b64":"eFnA/AbvTEADeaUmfZBGlZ+tr4gtmQbaf1pK1RWLtAnXFO3HpnViegPPUDj9jQfC/Un9AdaPvwJnD0SdyBMOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4316df093140285065b45cf846a3a384b888813392130da0eb269a83c405c863","last_reissued_at":"2026-07-28T02:23:32.096967Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:32.096967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.05540","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":"2026-07-28T02:23:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUclOWwREAqoYy4SrZHwo7qLUdWqybnRoaocRfZtntloW2VqnduBvfv6ZEqbt1nAmTmaBuCZWf/7BMS1fahMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:15:49.210392Z"},"content_sha256":"cb4c7afa4c97013d6c198382adaae7292605193cf3521e1223b6aa752e439cd9","schema_version":"1.0","event_id":"sha256:cb4c7afa4c97013d6c198382adaae7292605193cf3521e1223b6aa752e439cd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IMLN6CJRIAUFAZNULT4ENI5DQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autoregressive One-Step Generative Modeling for Dynamical System Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Tianyue Yang, Xiao Xue","submitted_at":"2026-05-07T00:41:47Z","abstract_excerpt":"Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories. Neural operators provide inexpensive autoregressive forecasts but can drift in turbulent regimes, whereas rolling diffusion and latent generative surrogates can represent stochastic transitions at the cost of multi-step denoising, noise-schedule design, or auxiliary compression models. We propose MeanFlow Long-term Invariant Spatiotemporal Consistency Autoregressive Models (MeLISA), a lat"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"MeLISA outperforms neural-operator baselines on short-term forecasting accuracy and long-horizon statistical metrics, including energy spectra, turbulent kinetic energy, and mixing-rate-related dynamics, while achieving inference speeds comparable to, and in some cases faster than, neural operators.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Window-Consistency MeanFlow objective combined with the Time Increment Consistency loss will stabilize long-horizon rollouts and preserve statistical structure without introducing artifacts or requiring additional post-hoc corrections.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"18cc15c8695950694f583b60c13a1d1c838a401f9e97fc915f1ca26514fb075e"},"source":{"id":"2605.05540","kind":"arxiv","version":2},"verdict":{"id":"94c39118-f062-4ccc-9b78-ce0b28e02ef8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T15:09:45.214445Z","strongest_claim":"MeLISA outperforms neural-operator baselines on short-term forecasting accuracy and long-horizon statistical metrics, including energy spectra, turbulent kinetic energy, and mixing-rate-related dynamics, while achieving inference speeds comparable to, and in some cases faster than, neural operators.","one_line_summary":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Window-Consistency MeanFlow objective combined with the Time Increment Consistency loss will stabilize long-horizon rollouts and preserve statistical structure without introducing artifacts or requiring additional post-hoc corrections.","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05540/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T14:02:04.792437Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T09:39:54.728897Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8c521cc8dedc5f7b3bd3cdfe1fd9d017226fc8a3958245a2e01e8982a34b74c6"},"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":"94c39118-f062-4ccc-9b78-ce0b28e02ef8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T02:23:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EyO+JYjBCYsx9F07hWWM/ljxr2RLE3xb0yaLAv3a0y7+Jc5JicQuTmRPdJDqwiyS3ukZRa+u3yyImPit1QuKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:15:49.212551Z"},"content_sha256":"f8ffaae3b7fd4688c6744327d949c3d55346bef2a98c36152023bb4228655f82","schema_version":"1.0","event_id":"sha256:f8ffaae3b7fd4688c6744327d949c3d55346bef2a98c36152023bb4228655f82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/bundle.json","state_url":"https://pith.science/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/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":"2026-08-03T14:15:49Z","links":{"resolver":"https://pith.science/pith/IMLN6CJRIAUFAZNULT4ENI5DQS","bundle":"https://pith.science/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/bundle.json","state":"https://pith.science/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMLN6CJRIAUFAZNULT4ENI5DQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMLN6CJRIAUFAZNULT4ENI5DQS","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":"2f6a418b0e469850555349606e8328c08aa9a251b6f6c5fcb6bdc36f8e6b54c0","cross_cats_sorted":["physics.flu-dyn"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T00:41:47Z","title_canon_sha256":"ecd340cccd0642893ab85be5612af305bc910bd69c266ffc229f3f8638a02da0"},"schema_version":"1.0","source":{"id":"2605.05540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05540","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05540v2","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05540","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"IMLN6CJRIAUF","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"IMLN6CJRIAUFAZNU","created_at":"2026-07-28T02:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"IMLN6CJR","created_at":"2026-07-28T02:23:32Z"}],"graph_snapshots":[{"event_id":"sha256:f8ffaae3b7fd4688c6744327d949c3d55346bef2a98c36152023bb4228655f82","target":"graph","created_at":"2026-07-28T02:23:32Z","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":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MeLISA outperforms neural-operator baselines on short-term forecasting accuracy and long-horizon statistical metrics, including energy spectra, turbulent kinetic energy, and mixing-rate-related dynamics, while achieving inference speeds comparable to, and in some cases faster than, neural operators."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Window-Consistency MeanFlow objective combined with the Time Increment Consistency loss will stabilize long-horizon rollouts and preserve statistical structure without introducing artifacts or requiring additional post-hoc corrections."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed."}],"snapshot_sha256":"18cc15c8695950694f583b60c13a1d1c838a401f9e97fc915f1ca26514fb075e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T14:02:04.792437Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T09:39:54.728897Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.05540/integrity.json","findings":[],"snapshot_sha256":"8c521cc8dedc5f7b3bd3cdfe1fd9d017226fc8a3958245a2e01e8982a34b74c6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories. Neural operators provide inexpensive autoregressive forecasts but can drift in turbulent regimes, whereas rolling diffusion and latent generative surrogates can represent stochastic transitions at the cost of multi-step denoising, noise-schedule design, or auxiliary compression models. We propose MeanFlow Long-term Invariant Spatiotemporal Consistency Autoregressive Models (MeLISA), a lat","authors_text":"Tianyue Yang, Xiao Xue","cross_cats":["physics.flu-dyn"],"headline":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T00:41:47Z","title":"Autoregressive One-Step Generative Modeling for Dynamical System Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.05540","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T15:09:45.214445Z","id":"94c39118-f062-4ccc-9b78-ce0b28e02ef8","model_set":{"reader":"grok-4.3"},"one_line_summary":"MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"MeLISA outperforms neural-operator baselines on short-term forecasting accuracy and long-horizon statistical metrics, including energy spectra, turbulent kinetic energy, and mixing-rate-related dynamics, while achieving inference speeds comparable to, and in some cases faster than, neural operators.","weakest_assumption":"That the Window-Consistency MeanFlow objective combined with the Time Increment Consistency loss will stabilize long-horizon rollouts and preserve statistical structure without introducing artifacts or requiring additional post-hoc corrections."}},"verdict_id":"94c39118-f062-4ccc-9b78-ce0b28e02ef8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cb4c7afa4c97013d6c198382adaae7292605193cf3521e1223b6aa752e439cd9","target":"record","created_at":"2026-07-28T02:23:32Z","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":"2f6a418b0e469850555349606e8328c08aa9a251b6f6c5fcb6bdc36f8e6b54c0","cross_cats_sorted":["physics.flu-dyn"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T00:41:47Z","title_canon_sha256":"ecd340cccd0642893ab85be5612af305bc910bd69c266ffc229f3f8638a02da0"},"schema_version":"1.0","source":{"id":"2605.05540","kind":"arxiv","version":2}},"canonical_sha256":"4316df093140285065b45cf846a3a384b888813392130da0eb269a83c405c863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4316df093140285065b45cf846a3a384b888813392130da0eb269a83c405c863","first_computed_at":"2026-07-28T02:23:32.096967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:32.096967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eFnA/AbvTEADeaUmfZBGlZ+tr4gtmQbaf1pK1RWLtAnXFO3HpnViegPPUDj9jQfC/Un9AdaPvwJnD0SdyBMOAA==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:32.098172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.05540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb4c7afa4c97013d6c198382adaae7292605193cf3521e1223b6aa752e439cd9","sha256:f8ffaae3b7fd4688c6744327d949c3d55346bef2a98c36152023bb4228655f82"],"state_sha256":"01c3eb37ae9b5594dde2d92693c1773de8922205ff6285a96c31f6841857a251"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"923b8PcKf5qhVmGcM66yYgPcDLvYM4t4BuIi+UYLHZ5rVpSytwp042L8gDsGRsfZn33R791odDaAhvsaprC6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:15:49.218722Z","bundle_sha256":"b48a5c68452650f3373b13267d9c7d2df154e6c88bbfa21569d42f8cb69523fb"}}