{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XVIIZEHCSLDZ3E3IS6H4JTV2FC","short_pith_number":"pith:XVIIZEHC","schema_version":"1.0","canonical_sha256":"bd508c90e292c79d9368978fc4ceba2887de281f6b3f2a9f2242129c755bb36a","source":{"kind":"arxiv","id":"2201.09113","version":4},"attestation_state":"computed","paper":{"title":"Predicting Physics in Mesh-reduced Space with Temporal Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han Gao, Jian-Xun Wang, Li-Ping Liu, Tobias Pfaff, Xu Han","submitted_at":"2022-01-22T18:32:54Z","abstract_excerpt":"Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short temporal attention span, these models suffer from error accumulation and drift. In this paper, we propose a new method that captures long-term dependencies through a transformer-style temporal attention model. We introduce an encoder-decoder structure to summarize features and create a compact mesh representation of the system state, to allow the temporal model to operate on a low-dimensional mesh representations in a "},"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":"2201.09113","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-22T18:32:54Z","cross_cats_sorted":[],"title_canon_sha256":"53e85e40641336c01e06f5aa9b709bed2d0cf2634a30ed844cec89d04869d20b","abstract_canon_sha256":"b8b44d9be6895d6c0a2c8a34bfb9996043e65ae2fb5415f5337da59d710dca35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:35.669624Z","signature_b64":"i8hIXWZ1Iq3B2D8aFNY3GReDo6Hh8WPVrdR0OWrRE89y/is8m4UZn6SFzl/avZ6KW2VTtlybzZIHvfxLNK72DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd508c90e292c79d9368978fc4ceba2887de281f6b3f2a9f2242129c755bb36a","last_reissued_at":"2026-07-05T04:26:35.669058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:35.669058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Physics in Mesh-reduced Space with Temporal Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han Gao, Jian-Xun Wang, Li-Ping Liu, Tobias Pfaff, Xu Han","submitted_at":"2022-01-22T18:32:54Z","abstract_excerpt":"Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short temporal attention span, these models suffer from error accumulation and drift. In this paper, we propose a new method that captures long-term dependencies through a transformer-style temporal attention model. We introduce an encoder-decoder structure to summarize features and create a compact mesh representation of the system state, to allow the temporal model to operate on a low-dimensional mesh representations in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09113","kind":"arxiv","version":4},"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/2201.09113/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":"2201.09113","created_at":"2026-07-05T04:26:35.669134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.09113v4","created_at":"2026-07-05T04:26:35.669134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09113","created_at":"2026-07-05T04:26:35.669134+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVIIZEHCSLDZ","created_at":"2026-07-05T04:26:35.669134+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVIIZEHCSLDZ3E3I","created_at":"2026-07-05T04:26:35.669134+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVIIZEHC","created_at":"2026-07-05T04:26:35.669134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00460","citing_title":"A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15767","citing_title":"Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":244,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":244,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14350","citing_title":"Weak-DMD: A Galerkin approach to the problem of noise in the Dynamic Mode Decomposition algorithm","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC","json":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC.json","graph_json":"https://pith.science/api/pith-number/XVIIZEHCSLDZ3E3IS6H4JTV2FC/graph.json","events_json":"https://pith.science/api/pith-number/XVIIZEHCSLDZ3E3IS6H4JTV2FC/events.json","paper":"https://pith.science/paper/XVIIZEHC"},"agent_actions":{"view_html":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC","download_json":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC.json","view_paper":"https://pith.science/paper/XVIIZEHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.09113&json=true","fetch_graph":"https://pith.science/api/pith-number/XVIIZEHCSLDZ3E3IS6H4JTV2FC/graph.json","fetch_events":"https://pith.science/api/pith-number/XVIIZEHCSLDZ3E3IS6H4JTV2FC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC/action/storage_attestation","attest_author":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC/action/author_attestation","sign_citation":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC/action/citation_signature","submit_replication":"https://pith.science/pith/XVIIZEHCSLDZ3E3IS6H4JTV2FC/action/replication_record"}},"created_at":"2026-07-05T04:26:35.669134+00:00","updated_at":"2026-07-05T04:26:35.669134+00:00"}