{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NOVTFCGHT2LHNQW6F5HERKP47V","short_pith_number":"pith:NOVTFCGH","schema_version":"1.0","canonical_sha256":"6bab3288c79e9676c2de2f4e48a9fcfd5d8aef2ea0ad0e11ff7456af4363d888","source":{"kind":"arxiv","id":"2503.24320","version":2},"attestation_state":"computed","paper":{"title":"Can Test-Time Scaling Improve World Foundation Model?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangya Liu, David Z. Pan, Dejia Xu, Hanqing Zhu, Kevin Wang, Peihao Wang, Wenyan Cong, Yan Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2025-03-31T17:07:37Z","abstract_excerpt":"World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical intelligence, including autonomous driving and robotics. However, these models require substantial computational resources for pretraining and are further constrained by available data during post-training. As such, scaling computation at test time emerges as both a critical and practical alternative to traditional model enlargement or re-training. In this work, we introduce SWIFT, a test-time scaling framework tailore"},"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":"2503.24320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T17:07:37Z","cross_cats_sorted":[],"title_canon_sha256":"65d5bb577087e2800ed94bad5d80ee1b2f142211732d7e79a87b042bdd825600","abstract_canon_sha256":"9a167737060c1c0d1f818166d37593dde294aa995c88abf987017ef70a62af14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:34.326452Z","signature_b64":"cZf9KQVtQDx+YHtA71k6/O312bgaNp0NNJeaRutEBICWDrV6Juplwc5PjXNLRr9VY3+aoclzB2tIpyaoF28GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bab3288c79e9676c2de2f4e48a9fcfd5d8aef2ea0ad0e11ff7456af4363d888","last_reissued_at":"2026-07-05T11:50:34.326015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:34.326015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Test-Time Scaling Improve World Foundation Model?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangya Liu, David Z. Pan, Dejia Xu, Hanqing Zhu, Kevin Wang, Peihao Wang, Wenyan Cong, Yan Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2025-03-31T17:07:37Z","abstract_excerpt":"World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical intelligence, including autonomous driving and robotics. However, these models require substantial computational resources for pretraining and are further constrained by available data during post-training. As such, scaling computation at test time emerges as both a critical and practical alternative to traditional model enlargement or re-training. In this work, we introduce SWIFT, a test-time scaling framework tailore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24320","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/2503.24320/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":"2503.24320","created_at":"2026-07-05T11:50:34.326077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.24320v2","created_at":"2026-07-05T11:50:34.326077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24320","created_at":"2026-07-05T11:50:34.326077+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOVTFCGHT2LH","created_at":"2026-07-05T11:50:34.326077+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOVTFCGHT2LHNQW6","created_at":"2026-07-05T11:50:34.326077+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOVTFCGH","created_at":"2026-07-05T11:50:34.326077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28757","citing_title":"A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03530","citing_title":"How Far Are We from Generating Missing Modalities with Foundation Models?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10841","citing_title":"Harnessing Photonics for Machine Intelligence","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V","json":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V.json","graph_json":"https://pith.science/api/pith-number/NOVTFCGHT2LHNQW6F5HERKP47V/graph.json","events_json":"https://pith.science/api/pith-number/NOVTFCGHT2LHNQW6F5HERKP47V/events.json","paper":"https://pith.science/paper/NOVTFCGH"},"agent_actions":{"view_html":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V","download_json":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V.json","view_paper":"https://pith.science/paper/NOVTFCGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.24320&json=true","fetch_graph":"https://pith.science/api/pith-number/NOVTFCGHT2LHNQW6F5HERKP47V/graph.json","fetch_events":"https://pith.science/api/pith-number/NOVTFCGHT2LHNQW6F5HERKP47V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V/action/storage_attestation","attest_author":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V/action/author_attestation","sign_citation":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V/action/citation_signature","submit_replication":"https://pith.science/pith/NOVTFCGHT2LHNQW6F5HERKP47V/action/replication_record"}},"created_at":"2026-07-05T11:50:34.326077+00:00","updated_at":"2026-07-05T11:50:34.326077+00:00"}