{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UYUDP433PY6Z2PA42AYJJG6WYP","short_pith_number":"pith:UYUDP433","schema_version":"1.0","canonical_sha256":"a62837f37b7e3d9d3c1cd030949bd6c3f0d5cff7ddb0f427b6bb491b50f5a349","source":{"kind":"arxiv","id":"2405.14828","version":2},"attestation_state":"computed","paper":{"title":"Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Shi, Katherine Xu, Lingzhi Zhang","submitted_at":"2024-05-23T17:46:23Z","abstract_excerpt":"Recent advances in text-to-image (T2I) diffusion models have facilitated creative and photorealistic image synthesis. By varying the random seeds, we can generate many images for a fixed text prompt. Technically, the seed controls the initial noise and, in multi-step diffusion inference, the noise used for reparameterization at intermediate timesteps in the reverse diffusion process. However, the specific impact of the random seed on the generated images remains relatively unexplored. In this work, we conduct a large-scale scientific study into the impact of random seeds during diffusion infer"},"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":"2405.14828","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"d9eae2d59ce4af01b6ccade824cf1e9d682167e9c21e330710b005450a0b0c57","abstract_canon_sha256":"054d18a1beffafaaef594e613061d1c68c202c1d81d550f001e71eab929bce99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:08.453533Z","signature_b64":"u9xOWK/H1BV0WsR9JdYACxUiC0P5wfzthal+LaKQlPSJMUtaZDdW8sqD7E8poSDK1fqU4d4DpVU8UMiHk89eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62837f37b7e3d9d3c1cd030949bd6c3f0d5cff7ddb0f427b6bb491b50f5a349","last_reissued_at":"2026-07-05T10:50:08.453077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:08.453077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Shi, Katherine Xu, Lingzhi Zhang","submitted_at":"2024-05-23T17:46:23Z","abstract_excerpt":"Recent advances in text-to-image (T2I) diffusion models have facilitated creative and photorealistic image synthesis. By varying the random seeds, we can generate many images for a fixed text prompt. Technically, the seed controls the initial noise and, in multi-step diffusion inference, the noise used for reparameterization at intermediate timesteps in the reverse diffusion process. However, the specific impact of the random seed on the generated images remains relatively unexplored. In this work, we conduct a large-scale scientific study into the impact of random seeds during diffusion infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14828","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/2405.14828/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":"2405.14828","created_at":"2026-07-05T10:50:08.453131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14828v2","created_at":"2026-07-05T10:50:08.453131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14828","created_at":"2026-07-05T10:50:08.453131+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYUDP433PY6Z","created_at":"2026-07-05T10:50:08.453131+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYUDP433PY6Z2PA4","created_at":"2026-07-05T10:50:08.453131+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYUDP433","created_at":"2026-07-05T10:50:08.453131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06843","citing_title":"Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20536","citing_title":"The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP","json":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP.json","graph_json":"https://pith.science/api/pith-number/UYUDP433PY6Z2PA42AYJJG6WYP/graph.json","events_json":"https://pith.science/api/pith-number/UYUDP433PY6Z2PA42AYJJG6WYP/events.json","paper":"https://pith.science/paper/UYUDP433"},"agent_actions":{"view_html":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP","download_json":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP.json","view_paper":"https://pith.science/paper/UYUDP433","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14828&json=true","fetch_graph":"https://pith.science/api/pith-number/UYUDP433PY6Z2PA42AYJJG6WYP/graph.json","fetch_events":"https://pith.science/api/pith-number/UYUDP433PY6Z2PA42AYJJG6WYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP/action/storage_attestation","attest_author":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP/action/author_attestation","sign_citation":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP/action/citation_signature","submit_replication":"https://pith.science/pith/UYUDP433PY6Z2PA42AYJJG6WYP/action/replication_record"}},"created_at":"2026-07-05T10:50:08.453131+00:00","updated_at":"2026-07-05T10:50:08.453131+00:00"}