{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:42XOFUCWIQITL2WE2EN5R2OJVE","short_pith_number":"pith:42XOFUCW","schema_version":"1.0","canonical_sha256":"e6aee2d056441135eac4d11bd8e9c9a906e440c0c67c42a0fda5ad11b7b8363d","source":{"kind":"arxiv","id":"2301.13338","version":2},"attestation_state":"computed","paper":{"title":"Continuous Spatiotemporal Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Antonio H. de O. Fonseca, David van Dijk, Emanuele Zappala, Josue Ortega Caro","submitted_at":"2023-01-31T00:06:56Z","abstract_excerpt":"Modeling spatiotemporal dynamical systems is a fundamental challenge in machine learning. Transformer models have been very successful in NLP and computer vision where they provide interpretable representations of data. However, a limitation of transformers in modeling continuous dynamical systems is that they are fundamentally discrete time and space models and thus have no guarantees regarding continuous sampling. To address this challenge, we present the Continuous Spatiotemporal Transformer (CST), a new transformer architecture that is designed for the modeling of continuous systems. This "},"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":"2301.13338","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T00:06:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e9f046a76ccb524c0cf8d39f7a2cd61d9fe6427400eb1b3b5df335a71d4682c7","abstract_canon_sha256":"89bc917f841c6e6873a443ed3028d30901e55fe9a77afa01dfecb82e2286c865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:48.059293Z","signature_b64":"GO7gtgaLkjBkkdC4ExyYi1RpnGirAIi0mEXR324ckPWKnhoB/v2hTNq0AAvwZH2Ico9+21v6r2D6yx9oik/RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6aee2d056441135eac4d11bd8e9c9a906e440c0c67c42a0fda5ad11b7b8363d","last_reissued_at":"2026-07-05T06:35:48.058773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:48.058773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Spatiotemporal Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Antonio H. de O. Fonseca, David van Dijk, Emanuele Zappala, Josue Ortega Caro","submitted_at":"2023-01-31T00:06:56Z","abstract_excerpt":"Modeling spatiotemporal dynamical systems is a fundamental challenge in machine learning. Transformer models have been very successful in NLP and computer vision where they provide interpretable representations of data. However, a limitation of transformers in modeling continuous dynamical systems is that they are fundamentally discrete time and space models and thus have no guarantees regarding continuous sampling. To address this challenge, we present the Continuous Spatiotemporal Transformer (CST), a new transformer architecture that is designed for the modeling of continuous systems. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13338","kind":"arxiv","version":2},"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/2301.13338/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":"2301.13338","created_at":"2026-07-05T06:35:48.058831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13338v2","created_at":"2026-07-05T06:35:48.058831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13338","created_at":"2026-07-05T06:35:48.058831+00:00"},{"alias_kind":"pith_short_12","alias_value":"42XOFUCWIQIT","created_at":"2026-07-05T06:35:48.058831+00:00"},{"alias_kind":"pith_short_16","alias_value":"42XOFUCWIQITL2WE","created_at":"2026-07-05T06:35:48.058831+00:00"},{"alias_kind":"pith_short_8","alias_value":"42XOFUCW","created_at":"2026-07-05T06:35:48.058831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08153","citing_title":"ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE","json":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE.json","graph_json":"https://pith.science/api/pith-number/42XOFUCWIQITL2WE2EN5R2OJVE/graph.json","events_json":"https://pith.science/api/pith-number/42XOFUCWIQITL2WE2EN5R2OJVE/events.json","paper":"https://pith.science/paper/42XOFUCW"},"agent_actions":{"view_html":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE","download_json":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE.json","view_paper":"https://pith.science/paper/42XOFUCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13338&json=true","fetch_graph":"https://pith.science/api/pith-number/42XOFUCWIQITL2WE2EN5R2OJVE/graph.json","fetch_events":"https://pith.science/api/pith-number/42XOFUCWIQITL2WE2EN5R2OJVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE/action/storage_attestation","attest_author":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE/action/author_attestation","sign_citation":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE/action/citation_signature","submit_replication":"https://pith.science/pith/42XOFUCWIQITL2WE2EN5R2OJVE/action/replication_record"}},"created_at":"2026-07-05T06:35:48.058831+00:00","updated_at":"2026-07-05T06:35:48.058831+00:00"}