{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S4RYYHJ654DNO4YUSZOVB3NO24","short_pith_number":"pith:S4RYYHJ6","schema_version":"1.0","canonical_sha256":"97238c1d3eef06d77314965d50edaed70eda7f23626eda095f119ec2124e762b","source":{"kind":"arxiv","id":"2503.16400","version":3},"attestation_state":"computed","paper":{"title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feilong Tang, Haolin Yang, Imran Razzak, Junjun He, Ming Hu, Peng Gao, Qingyu Yin, Yexin Liu, Yulong Li, Zelin Peng, Zongyuan Ge","submitted_at":"2025-03-20T17:54:37Z","abstract_excerpt":"Video diffusion models (VDMs) facilitate the generation of high-quality videos, with current research predominantly concentrated on scaling efforts during training through improvements in data quality, computational resources, and model complexity. However, inference-time scaling has received less attention, with most approaches restricting models to a single generation attempt. Recent studies have uncovered the existence of \"golden noises\" that can enhance video quality during generation. Building on this, we find that guiding the scaling inference-time search of VDMs to identify better noise"},"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":"2503.16400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-20T17:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"b4411db35d948ae3fc0e74def7ad788fe5cd2b3521f57efa805f1e84f8adbe70","abstract_canon_sha256":"806344d935cacc0521ddb0fe5880ad594e78b84755cb58b87ba392a310e928fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:40.729605Z","signature_b64":"dXNLk4I9s59YLJhV19/HHN4/eg8EcVa3C8wX/lj7U9gIXCXBK5xZ0CZFrM6J8cTeiDzNQcV2EgqnMC/RBCnmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97238c1d3eef06d77314965d50edaed70eda7f23626eda095f119ec2124e762b","last_reissued_at":"2026-07-05T11:08:40.729137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:40.729137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feilong Tang, Haolin Yang, Imran Razzak, Junjun He, Ming Hu, Peng Gao, Qingyu Yin, Yexin Liu, Yulong Li, Zelin Peng, Zongyuan Ge","submitted_at":"2025-03-20T17:54:37Z","abstract_excerpt":"Video diffusion models (VDMs) facilitate the generation of high-quality videos, with current research predominantly concentrated on scaling efforts during training through improvements in data quality, computational resources, and model complexity. However, inference-time scaling has received less attention, with most approaches restricting models to a single generation attempt. Recent studies have uncovered the existence of \"golden noises\" that can enhance video quality during generation. Building on this, we find that guiding the scaling inference-time search of VDMs to identify better noise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16400","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/2503.16400/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":"2503.16400","created_at":"2026-07-05T11:08:40.729194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16400v3","created_at":"2026-07-05T11:08:40.729194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16400","created_at":"2026-07-05T11:08:40.729194+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4RYYHJ654DN","created_at":"2026-07-05T11:08:40.729194+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4RYYHJ654DNO4YU","created_at":"2026-07-05T11:08:40.729194+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4RYYHJ6","created_at":"2026-07-05T11:08:40.729194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24","json":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24.json","graph_json":"https://pith.science/api/pith-number/S4RYYHJ654DNO4YUSZOVB3NO24/graph.json","events_json":"https://pith.science/api/pith-number/S4RYYHJ654DNO4YUSZOVB3NO24/events.json","paper":"https://pith.science/paper/S4RYYHJ6"},"agent_actions":{"view_html":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24","download_json":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24.json","view_paper":"https://pith.science/paper/S4RYYHJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16400&json=true","fetch_graph":"https://pith.science/api/pith-number/S4RYYHJ654DNO4YUSZOVB3NO24/graph.json","fetch_events":"https://pith.science/api/pith-number/S4RYYHJ654DNO4YUSZOVB3NO24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24/action/storage_attestation","attest_author":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24/action/author_attestation","sign_citation":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24/action/citation_signature","submit_replication":"https://pith.science/pith/S4RYYHJ654DNO4YUSZOVB3NO24/action/replication_record"}},"created_at":"2026-07-05T11:08:40.729194+00:00","updated_at":"2026-07-05T11:08:40.729194+00:00"}