{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GVDWEMF37PXPHBCPQYLF4CMVGD","short_pith_number":"pith:GVDWEMF3","schema_version":"1.0","canonical_sha256":"35476230bbfbeef3844f86165e099530fd4a56057b6a0fd5bd71896c02ad2286","source":{"kind":"arxiv","id":"2506.01337","version":1},"attestation_state":"computed","paper":{"title":"NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heung-Yeung Shum, Ping Tan, Xiangyue Liu, Xiangyu Zhang, Zeming Li","submitted_at":"2025-06-02T05:32:35Z","abstract_excerpt":"Diffusion models have emerged as powerful generative frameworks, creating data samples by progressively denoising an initial random state. Traditionally, this initial state is sampled from a simple, fixed distribution like isotropic Gaussian, inherently lacking structure and a direct mechanism for external control. While recent efforts have explored ways to introduce controllability into the diffusion process, particularly at the initialization stage, they often rely on deterministic or heuristic approaches. These methods can be suboptimal, lack expressiveness, and are difficult to scale or in"},"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":"2506.01337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T05:32:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0d1d0d1c2deac6dedca1f314c07bf6659266508fbf12d57ef9973633917d055","abstract_canon_sha256":"db9cebefc645f821474838c48998210280531f09d0bbc00421ff1addef792f7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:11.935052Z","signature_b64":"d6WLRq3kv0xwNbmkoUiMnbQNR/IbLrlCj4YcbM2KYr+OcXhnHHUNaZrcjlURR3gSSfYc6B+oIvuCbvmCjax9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35476230bbfbeef3844f86165e099530fd4a56057b6a0fd5bd71896c02ad2286","last_reissued_at":"2026-07-05T11:14:11.934482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:11.934482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heung-Yeung Shum, Ping Tan, Xiangyue Liu, Xiangyu Zhang, Zeming Li","submitted_at":"2025-06-02T05:32:35Z","abstract_excerpt":"Diffusion models have emerged as powerful generative frameworks, creating data samples by progressively denoising an initial random state. Traditionally, this initial state is sampled from a simple, fixed distribution like isotropic Gaussian, inherently lacking structure and a direct mechanism for external control. While recent efforts have explored ways to introduce controllability into the diffusion process, particularly at the initialization stage, they often rely on deterministic or heuristic approaches. These methods can be suboptimal, lack expressiveness, and are difficult to scale or in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01337","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/2506.01337/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":"2506.01337","created_at":"2026-07-05T11:14:11.934565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01337v1","created_at":"2026-07-05T11:14:11.934565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01337","created_at":"2026-07-05T11:14:11.934565+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVDWEMF37PXP","created_at":"2026-07-05T11:14:11.934565+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVDWEMF37PXPHBCP","created_at":"2026-07-05T11:14:11.934565+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVDWEMF3","created_at":"2026-07-05T11:14:11.934565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05478","citing_title":"Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07253","citing_title":"LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD","json":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD.json","graph_json":"https://pith.science/api/pith-number/GVDWEMF37PXPHBCPQYLF4CMVGD/graph.json","events_json":"https://pith.science/api/pith-number/GVDWEMF37PXPHBCPQYLF4CMVGD/events.json","paper":"https://pith.science/paper/GVDWEMF3"},"agent_actions":{"view_html":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD","download_json":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD.json","view_paper":"https://pith.science/paper/GVDWEMF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01337&json=true","fetch_graph":"https://pith.science/api/pith-number/GVDWEMF37PXPHBCPQYLF4CMVGD/graph.json","fetch_events":"https://pith.science/api/pith-number/GVDWEMF37PXPHBCPQYLF4CMVGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD/action/storage_attestation","attest_author":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD/action/author_attestation","sign_citation":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD/action/citation_signature","submit_replication":"https://pith.science/pith/GVDWEMF37PXPHBCPQYLF4CMVGD/action/replication_record"}},"created_at":"2026-07-05T11:14:11.934565+00:00","updated_at":"2026-07-05T11:14:11.934565+00:00"}