{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y25SPYVCBA7NQO4C5SFEPKBF5E","short_pith_number":"pith:Y25SPYVC","canonical_record":{"source":{"id":"2605.13790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:11:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4347236433d53a8365c7fbd3b4f737d804f229daae4dc15b148a6339e8e8c1df","abstract_canon_sha256":"25567fccfddb85009f9f975376adc3c0f6b6fc681e5598cf2faf8742498237cc"},"schema_version":"1.0"},"canonical_sha256":"c6bb27e2a2083ed83b82ec8a47a825e935c6096b7345bb81737dc4c2bbf0218f","source":{"kind":"arxiv","id":"2605.13790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13790","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13790v1","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13790","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"Y25SPYVCBA7N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y25SPYVCBA7NQO4C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y25SPYVC","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y25SPYVCBA7NQO4C5SFEPKBF5E","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:11:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4347236433d53a8365c7fbd3b4f737d804f229daae4dc15b148a6339e8e8c1df","abstract_canon_sha256":"25567fccfddb85009f9f975376adc3c0f6b6fc681e5598cf2faf8742498237cc"},"schema_version":"1.0"},"canonical_sha256":"c6bb27e2a2083ed83b82ec8a47a825e935c6096b7345bb81737dc4c2bbf0218f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:15.627628Z","signature_b64":"q9tVGiaumGDi7Ps8sz6okmeZfFwG5aynYii7TeVcM42s616Y8+YqjSPxbk04n3WUyTRDeJTUreXjMLHym3jwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6bb27e2a2083ed83b82ec8a47a825e935c6096b7345bb81737dc4c2bbf0218f","last_reissued_at":"2026-05-18T02:44:15.627127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:15.627127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13790","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":"2026-05-18T02:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8IcdSLnEaJByn0lnY3Sljn019DKekxYjq35/PxVJgqmTd4Mk4dNMtSolV0Y7X+HQdJQhRqJt05UMks0ZwYawCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:36:12.085858Z"},"content_sha256":"a0f7b77be5df7cb105b79a6f91413e3ca8c32e7acb7eb7c8967eb06999440f50","schema_version":"1.0","event_id":"sha256:a0f7b77be5df7cb105b79a6f91413e3ca8c32e7acb7eb7c8967eb06999440f50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y25SPYVCBA7NQO4C5SFEPKBF5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoyu Liu, Qian Zhang, Zhonghao Li","submitted_at":"2026-05-13T17:11:07Z","abstract_excerpt":"Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, observational data are extremely sparse, which severely limits the applicability of both classical numerical solvers and existing neural approaches. While neural methods have shown promising results under moderately sparse observations, their inference efficiency at high resolutions is limited, and their accuracy degrades substantially in the extremely sparse regime. In this work, we propose the Di-BiLPS, a unified neural framework that effectivel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the PDE-informed denoising algorithm operating in the learned latent space accurately recovers the underlying physics without introducing artifacts or bias when observations drop to 3% or lower.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Di-BiLPS combines a variational autoencoder, latent diffusion, and contrastive learning to achieve state-of-the-art accuracy on PDE problems with as little as 3% observations while supporting zero-shot super-resolution and lower computational cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a6e2f91b48fa10da482d6f0b75e79480025506cda287c02391d05ec240044720"},"source":{"id":"2605.13790","kind":"arxiv","version":1},"verdict":{"id":"9cca7915-f18a-4241-a500-50f9618f9fba","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:03:05.072216Z","strongest_claim":"Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains.","one_line_summary":"Di-BiLPS combines a variational autoencoder, latent diffusion, and contrastive learning to achieve state-of-the-art accuracy on PDE problems with as little as 3% observations while supporting zero-shot super-resolution and lower computational cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the PDE-informed denoising algorithm operating in the learned latent space accurately recovers the underlying physics without introducing artifacts or bias when observations drop to 3% or lower.","pith_extraction_headline":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space."},"references":{"count":21,"sample":[{"doi":"","year":null,"title":"World Simulation with Video Foundation Models for Physical AI","work_id":"1dc393b8-98c3-43bd-8ab0-25d7c2a9705b","ref_index":1,"cited_arxiv_id":"2511.00062","is_internal_anchor":true},{"doi":"","year":null,"title":"Universal physics Transformers","work_id":"2c0eb5d6-aed9-439b-8b33-6300205b7802","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"F., Stuart, A., Mahoney, M","work_id":"31cbb99f-58a0-46c6-8bc7-3066bd4ae554","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","work_id":"083ab9fb-05f0-41e1-9628-982017eac344","ref_index":4,"cited_arxiv_id":"2209.14687","is_internal_anchor":true},{"doi":"","year":2010,"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","ref_index":5,"cited_arxiv_id":"2010.11929","is_internal_anchor":true}],"resolved_work":21,"snapshot_sha256":"898ff6f8cc8f1f9d6a09a195d394ee8a7380f10672856387718f3844c47cd03d","internal_anchors":7},"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":"9cca7915-f18a-4241-a500-50f9618f9fba"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLykXdKYjHVsXcMaFvU4ONZRne7vezMGFfgDbkT4uwZIwYoKyLzQ6biQa3Xjy+ftkcrmg4bRZLxiKNRovqcCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:36:12.086865Z"},"content_sha256":"c33c48a6f44a64a736e9c5085847cf8a460d82a642f2ed873d43820912b75e42","schema_version":"1.0","event_id":"sha256:c33c48a6f44a64a736e9c5085847cf8a460d82a642f2ed873d43820912b75e42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/bundle.json","state_url":"https://pith.science/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/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":"2026-06-01T02:36:12Z","links":{"resolver":"https://pith.science/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E","bundle":"https://pith.science/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/bundle.json","state":"https://pith.science/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y25SPYVCBA7NQO4C5SFEPKBF5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y25SPYVCBA7NQO4C5SFEPKBF5E","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":"25567fccfddb85009f9f975376adc3c0f6b6fc681e5598cf2faf8742498237cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:11:07Z","title_canon_sha256":"4347236433d53a8365c7fbd3b4f737d804f229daae4dc15b148a6339e8e8c1df"},"schema_version":"1.0","source":{"id":"2605.13790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13790","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13790v1","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13790","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"Y25SPYVCBA7N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y25SPYVCBA7NQO4C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y25SPYVC","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c33c48a6f44a64a736e9c5085847cf8a460d82a642f2ed873d43820912b75e42","target":"graph","created_at":"2026-05-18T02:44:15Z","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":"Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the PDE-informed denoising algorithm operating in the learned latent space accurately recovers the underlying physics without introducing artifacts or bias when observations drop to 3% or lower."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Di-BiLPS combines a variational autoencoder, latent diffusion, and contrastive learning to achieve state-of-the-art accuracy on PDE problems with as little as 3% observations while supporting zero-shot super-resolution and lower computational cost."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space."}],"snapshot_sha256":"a6e2f91b48fa10da482d6f0b75e79480025506cda287c02391d05ec240044720"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, observational data are extremely sparse, which severely limits the applicability of both classical numerical solvers and existing neural approaches. While neural methods have shown promising results under moderately sparse observations, their inference efficiency at high resolutions is limited, and their accuracy degrades substantially in the extremely sparse regime. In this work, we propose the Di-BiLPS, a unified neural framework that effectivel","authors_text":"Chaoyu Liu, Qian Zhang, Zhonghao Li","cross_cats":["cs.AI"],"headline":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:11:07Z","title":"Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations"},"references":{"count":21,"internal_anchors":7,"resolved_work":21,"sample":[{"cited_arxiv_id":"2511.00062","doi":"","is_internal_anchor":true,"ref_index":1,"title":"World Simulation with Video Foundation Models for Physical AI","work_id":"1dc393b8-98c3-43bd-8ab0-25d7c2a9705b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Universal physics Transformers","work_id":"2c0eb5d6-aed9-439b-8b33-6300205b7802","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"F., Stuart, A., Mahoney, M","work_id":"31cbb99f-58a0-46c6-8bc7-3066bd4ae554","year":2025},{"cited_arxiv_id":"2209.14687","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","work_id":"083ab9fb-05f0-41e1-9628-982017eac344","year":null},{"cited_arxiv_id":"2010.11929","doi":"","is_internal_anchor":true,"ref_index":5,"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","year":2010}],"snapshot_sha256":"898ff6f8cc8f1f9d6a09a195d394ee8a7380f10672856387718f3844c47cd03d"},"source":{"id":"2605.13790","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:03:05.072216Z","id":"9cca7915-f18a-4241-a500-50f9618f9fba","model_set":{"reader":"grok-4.3"},"one_line_summary":"Di-BiLPS combines a variational autoencoder, latent diffusion, and contrastive learning to achieve state-of-the-art accuracy on PDE problems with as little as 3% observations while supporting zero-shot super-resolution and lower computational cost.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Di-BiLPS solves both forward and inverse PDE problems from as little as 3 percent sparse observations by operating entirely in a compressed latent space.","strongest_claim":"Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains.","weakest_assumption":"That the PDE-informed denoising algorithm operating in the learned latent space accurately recovers the underlying physics without introducing artifacts or bias when observations drop to 3% or lower."}},"verdict_id":"9cca7915-f18a-4241-a500-50f9618f9fba"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a0f7b77be5df7cb105b79a6f91413e3ca8c32e7acb7eb7c8967eb06999440f50","target":"record","created_at":"2026-05-18T02:44:15Z","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":"25567fccfddb85009f9f975376adc3c0f6b6fc681e5598cf2faf8742498237cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:11:07Z","title_canon_sha256":"4347236433d53a8365c7fbd3b4f737d804f229daae4dc15b148a6339e8e8c1df"},"schema_version":"1.0","source":{"id":"2605.13790","kind":"arxiv","version":1}},"canonical_sha256":"c6bb27e2a2083ed83b82ec8a47a825e935c6096b7345bb81737dc4c2bbf0218f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6bb27e2a2083ed83b82ec8a47a825e935c6096b7345bb81737dc4c2bbf0218f","first_computed_at":"2026-05-18T02:44:15.627127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:15.627127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q9tVGiaumGDi7Ps8sz6okmeZfFwG5aynYii7TeVcM42s616Y8+YqjSPxbk04n3WUyTRDeJTUreXjMLHym3jwDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:15.627628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f7b77be5df7cb105b79a6f91413e3ca8c32e7acb7eb7c8967eb06999440f50","sha256:c33c48a6f44a64a736e9c5085847cf8a460d82a642f2ed873d43820912b75e42"],"state_sha256":"1cc18ab689f9e3b9f0d2fe43bbf97e2887de0be3c5452f932be81e7ab8243c03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urKDs1q9yZDWlzqXkr8e+GLfwsipMPUxkhsKiRHmkYqNAZQqpmDdCnmh+w9L2v1SK4OpKb2PvIOn26SHZSH9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:36:12.092944Z","bundle_sha256":"b24115656c91222ef2fa07b2ca42f8e7ba1c0971d41b61cdb3e11d7599a872e5"}}