{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIB7PST7MOTAFSIAIKDLOSIFTS","short_pith_number":"pith:JIB7PST7","schema_version":"1.0","canonical_sha256":"4a03f7ca7f63a602c9004286b749059cbf338b1851cff109f1eb0b1e093c85bd","source":{"kind":"arxiv","id":"2505.17618","version":1},"attestation_state":"computed","paper":{"title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haoran He, Jiajun Liang, Kun Gai, Ling Pan, Pengfei Wan, Xintao Wang","submitted_at":"2025-05-23T08:25:46Z","abstract_excerpt":"As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising direction for improving generative model performance by allocating additional computation at inference time. While TTS has demonstrated significant success across multiple language tasks, there remains a notable gap in understanding the test-time scaling behaviors of image and video generative models (diffusion-based or flow-based models). Although recent works have initiated exploration into inference-time strategie"},"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":"2505.17618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T08:25:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a81d4ebde5b45fd029cdd19dafb375ee27f5527effab37f6f09b7c65c0e2074","abstract_canon_sha256":"f6000f60c2226eab0cad368003054be9d61ae1d28443db2350025e4bf7c448f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:29.415887Z","signature_b64":"n12FddMmJBsWYUa6G81TtkiSDj0FiAbeSDbOyUQe//0PEq4zlnCkT49tlNxF5rZpz3i6/El+QuCq1uO1rOitDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a03f7ca7f63a602c9004286b749059cbf338b1851cff109f1eb0b1e093c85bd","last_reissued_at":"2026-07-05T11:08:29.415379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:29.415379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haoran He, Jiajun Liang, Kun Gai, Ling Pan, Pengfei Wan, Xintao Wang","submitted_at":"2025-05-23T08:25:46Z","abstract_excerpt":"As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising direction for improving generative model performance by allocating additional computation at inference time. While TTS has demonstrated significant success across multiple language tasks, there remains a notable gap in understanding the test-time scaling behaviors of image and video generative models (diffusion-based or flow-based models). Although recent works have initiated exploration into inference-time strategie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17618","kind":"arxiv","version":1},"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/2505.17618/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":"2505.17618","created_at":"2026-07-05T11:08:29.415440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17618v1","created_at":"2026-07-05T11:08:29.415440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17618","created_at":"2026-07-05T11:08:29.415440+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIB7PST7MOTA","created_at":"2026-07-05T11:08:29.415440+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIB7PST7MOTAFSIA","created_at":"2026-07-05T11:08:29.415440+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIB7PST7","created_at":"2026-07-05T11:08:29.415440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26551","citing_title":"PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11969","citing_title":"SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08393","citing_title":"SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03183","citing_title":"Inference-Time Scaling for Joint Audio-Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02564","citing_title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02564","citing_title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26551","citing_title":"PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19317","citing_title":"Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08735","citing_title":"CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08144","citing_title":"NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04461","citing_title":"Stream-T1: Test-Time Scaling for Streaming Video Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS","json":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS.json","graph_json":"https://pith.science/api/pith-number/JIB7PST7MOTAFSIAIKDLOSIFTS/graph.json","events_json":"https://pith.science/api/pith-number/JIB7PST7MOTAFSIAIKDLOSIFTS/events.json","paper":"https://pith.science/paper/JIB7PST7"},"agent_actions":{"view_html":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS","download_json":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS.json","view_paper":"https://pith.science/paper/JIB7PST7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17618&json=true","fetch_graph":"https://pith.science/api/pith-number/JIB7PST7MOTAFSIAIKDLOSIFTS/graph.json","fetch_events":"https://pith.science/api/pith-number/JIB7PST7MOTAFSIAIKDLOSIFTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS/action/storage_attestation","attest_author":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS/action/author_attestation","sign_citation":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS/action/citation_signature","submit_replication":"https://pith.science/pith/JIB7PST7MOTAFSIAIKDLOSIFTS/action/replication_record"}},"created_at":"2026-07-05T11:08:29.415440+00:00","updated_at":"2026-07-05T11:08:29.415440+00:00"}