{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K4PKIDK7UYT62J4DORMZ5NEMB7","short_pith_number":"pith:K4PKIDK7","schema_version":"1.0","canonical_sha256":"571ea40d5fa627ed278374599eb48c0fe2afdd4b0dded6c691998f911d69265a","source":{"kind":"arxiv","id":"2410.03437","version":3},"attestation_state":"computed","paper":{"title":"Zebra: In-Context Generative Pretraining for Solving Parametric PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Armand Kassa\\\"i Koupa\\\"i, Louis Serrano, Patrick Gallinari, Pierre Erbacher, Thomas X Wang","submitted_at":"2024-10-04T13:52:02Z","abstract_excerpt":"Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing terms, and initial conditions. State-of-the-art neural surrogates perform adaptation through gradient-based optimization and meta-learning to implicitly encode the variety of dynamics from observations. This often comes with increased inference complexity. Inspired by the in-context learning capabilities of large language models (LLMs), we introduce Zebra, a novel generative auto-regressive transform"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.03437","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T13:52:02Z","cross_cats_sorted":[],"title_canon_sha256":"37eed07535e13bf68837ebb701befefcc23c4f30ea1705263f8c456830380993","abstract_canon_sha256":"2ebcf0dd6ea4265ddaaed86e3ce056486dcbf32cf508b7fb0f52157080bbeffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:49.806469Z","signature_b64":"Ge/VCDvkMaoh2ISJQDROKTKweWsaTRBkWV7mDQ1XOVV8DNxcTi3EJ/X3zRuG7jbfxqspzA5GAhg4ipa1aXjCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"571ea40d5fa627ed278374599eb48c0fe2afdd4b0dded6c691998f911d69265a","last_reissued_at":"2026-07-05T11:27:49.805823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:49.805823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zebra: In-Context Generative Pretraining for Solving Parametric PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Armand Kassa\\\"i Koupa\\\"i, Louis Serrano, Patrick Gallinari, Pierre Erbacher, Thomas X Wang","submitted_at":"2024-10-04T13:52:02Z","abstract_excerpt":"Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing terms, and initial conditions. State-of-the-art neural surrogates perform adaptation through gradient-based optimization and meta-learning to implicitly encode the variety of dynamics from observations. This often comes with increased inference complexity. Inspired by the in-context learning capabilities of large language models (LLMs), we introduce Zebra, a novel generative auto-regressive transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03437","kind":"arxiv","version":3},"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/2410.03437/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.03437","created_at":"2026-07-05T11:27:49.805900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03437v3","created_at":"2026-07-05T11:27:49.805900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03437","created_at":"2026-07-05T11:27:49.805900+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4PKIDK7UYT6","created_at":"2026-07-05T11:27:49.805900+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4PKIDK7UYT62J4D","created_at":"2026-07-05T11:27:49.805900+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4PKIDK7","created_at":"2026-07-05T11:27:49.805900+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12318","citing_title":"Harness In-Context Operator Learning with Chain of Operators","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7","json":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7.json","graph_json":"https://pith.science/api/pith-number/K4PKIDK7UYT62J4DORMZ5NEMB7/graph.json","events_json":"https://pith.science/api/pith-number/K4PKIDK7UYT62J4DORMZ5NEMB7/events.json","paper":"https://pith.science/paper/K4PKIDK7"},"agent_actions":{"view_html":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7","download_json":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7.json","view_paper":"https://pith.science/paper/K4PKIDK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03437&json=true","fetch_graph":"https://pith.science/api/pith-number/K4PKIDK7UYT62J4DORMZ5NEMB7/graph.json","fetch_events":"https://pith.science/api/pith-number/K4PKIDK7UYT62J4DORMZ5NEMB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7/action/storage_attestation","attest_author":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7/action/author_attestation","sign_citation":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7/action/citation_signature","submit_replication":"https://pith.science/pith/K4PKIDK7UYT62J4DORMZ5NEMB7/action/replication_record"}},"created_at":"2026-07-05T11:27:49.805900+00:00","updated_at":"2026-07-05T11:27:49.805900+00:00"}