{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SVKVQ3HZYY5XBJRPIISV32PA47","short_pith_number":"pith:SVKVQ3HZ","schema_version":"1.0","canonical_sha256":"9555586cf9c63b70a62f42255de9e0e7d97b9d3ddbe9383e327de9305cfe9e7d","source":{"kind":"arxiv","id":"2607.23488","version":1},"attestation_state":"computed","paper":{"title":"Learning Sampling Parameters for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arisrei Lim, Yossi Gandelsman","submitted_at":"2026-07-26T06:29:48Z","abstract_excerpt":"Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values. We introduce LeSAMP, a framework for learning prompt-conditioned, timestep-varying sampling parameters. We formulate parameter selection as a reinforcement learning problem: Given a user prompt, a large language model "},"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":"2607.23488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T06:29:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54bf0dba240aa216e0104471a1e4885594009453a9185fb2d0ea66edddd44502","abstract_canon_sha256":"cd0e251155d5e9ebe35ca3f36913b8451860c363bc70409057b7ad50a83470e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:55.560290Z","signature_b64":"1Ih8xaHqj6UWmglCkQvEDxiTrqrKmj93G59ZvSDVgQNaBd7hbuFEP+NvZBkHOdN5PDbSDLbdb9zEtvouhQQwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9555586cf9c63b70a62f42255de9e0e7d97b9d3ddbe9383e327de9305cfe9e7d","last_reissued_at":"2026-07-28T01:22:55.559138Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:55.559138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sampling Parameters for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arisrei Lim, Yossi Gandelsman","submitted_at":"2026-07-26T06:29:48Z","abstract_excerpt":"Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values. We introduce LeSAMP, a framework for learning prompt-conditioned, timestep-varying sampling parameters. We formulate parameter selection as a reinforcement learning problem: Given a user prompt, a large language model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23488","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/2607.23488/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":"2607.23488","created_at":"2026-07-28T01:22:55.559847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23488v1","created_at":"2026-07-28T01:22:55.559847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23488","created_at":"2026-07-28T01:22:55.559847+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVKVQ3HZYY5X","created_at":"2026-07-28T01:22:55.559847+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVKVQ3HZYY5XBJRP","created_at":"2026-07-28T01:22:55.559847+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVKVQ3HZ","created_at":"2026-07-28T01:22:55.559847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47","json":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47.json","graph_json":"https://pith.science/api/pith-number/SVKVQ3HZYY5XBJRPIISV32PA47/graph.json","events_json":"https://pith.science/api/pith-number/SVKVQ3HZYY5XBJRPIISV32PA47/events.json","paper":"https://pith.science/paper/SVKVQ3HZ"},"agent_actions":{"view_html":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47","download_json":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47.json","view_paper":"https://pith.science/paper/SVKVQ3HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23488&json=true","fetch_graph":"https://pith.science/api/pith-number/SVKVQ3HZYY5XBJRPIISV32PA47/graph.json","fetch_events":"https://pith.science/api/pith-number/SVKVQ3HZYY5XBJRPIISV32PA47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47/action/storage_attestation","attest_author":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47/action/author_attestation","sign_citation":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47/action/citation_signature","submit_replication":"https://pith.science/pith/SVKVQ3HZYY5XBJRPIISV32PA47/action/replication_record"}},"created_at":"2026-07-28T01:22:55.559847+00:00","updated_at":"2026-07-28T01:22:55.559847+00:00"}