{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BRSBSTGYSDA4YYSXLOVFHBYNH5","short_pith_number":"pith:BRSBSTGY","schema_version":"1.0","canonical_sha256":"0c64194cd890c1cc62575baa53870d3f7f39de6f2529c8f66d3029f5c728c23e","source":{"kind":"arxiv","id":"2601.01608","version":2},"attestation_state":"computed","paper":{"title":"Guiding Token-Sparse Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Felix Krause, Johannes Schusterbauer, Ming Gui, Olga Grebenkova, Stefan Andreas Baumann, Vincent Tao Hu","submitted_at":"2026-01-04T17:18:27Z","abstract_excerpt":"Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset of visual information. While these methods were successful in providing cheaper and more effective training, sparsely trained diffusion models struggle in inference. This is due to their lacking response to Classifier-free Guidance (CFG) leading to underwhelming performance during inference. To overcome this, we propose Sparse Guidance (SG). Instead of usin"},"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":"2601.01608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-04T17:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"2696e32edcca2178a4293341a0409ce312f2f345e1788c2f78ed32e55e9a53c3","abstract_canon_sha256":"8b3c0c6e0f29463e4aa693963ab36bab344278dadf49f4b7d7c859d68c2bddbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:09.904170Z","signature_b64":"BMjj8npB9q55zdnqWaBoD9YFn73d3+8slYo5M7P5MSS2PBxvMgn8JncZbGgsSnKDe80I0stel42fvoiA8EmfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c64194cd890c1cc62575baa53870d3f7f39de6f2529c8f66d3029f5c728c23e","last_reissued_at":"2026-05-27T02:05:09.903456Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:09.903456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guiding Token-Sparse Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Felix Krause, Johannes Schusterbauer, Ming Gui, Olga Grebenkova, Stefan Andreas Baumann, Vincent Tao Hu","submitted_at":"2026-01-04T17:18:27Z","abstract_excerpt":"Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset of visual information. While these methods were successful in providing cheaper and more effective training, sparsely trained diffusion models struggle in inference. This is due to their lacking response to Classifier-free Guidance (CFG) leading to underwhelming performance during inference. To overcome this, we propose Sparse Guidance (SG). Instead of usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.01608","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/2601.01608/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":"2601.01608","created_at":"2026-05-27T02:05:09.903539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.01608v2","created_at":"2026-05-27T02:05:09.903539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.01608","created_at":"2026-05-27T02:05:09.903539+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRSBSTGYSDA4","created_at":"2026-05-27T02:05:09.903539+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRSBSTGYSDA4YYSX","created_at":"2026-05-27T02:05:09.903539+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRSBSTGY","created_at":"2026-05-27T02:05:09.903539+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/BRSBSTGYSDA4YYSXLOVFHBYNH5","json":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5.json","graph_json":"https://pith.science/api/pith-number/BRSBSTGYSDA4YYSXLOVFHBYNH5/graph.json","events_json":"https://pith.science/api/pith-number/BRSBSTGYSDA4YYSXLOVFHBYNH5/events.json","paper":"https://pith.science/paper/BRSBSTGY"},"agent_actions":{"view_html":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5","download_json":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5.json","view_paper":"https://pith.science/paper/BRSBSTGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.01608&json=true","fetch_graph":"https://pith.science/api/pith-number/BRSBSTGYSDA4YYSXLOVFHBYNH5/graph.json","fetch_events":"https://pith.science/api/pith-number/BRSBSTGYSDA4YYSXLOVFHBYNH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5/action/storage_attestation","attest_author":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5/action/author_attestation","sign_citation":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5/action/citation_signature","submit_replication":"https://pith.science/pith/BRSBSTGYSDA4YYSXLOVFHBYNH5/action/replication_record"}},"created_at":"2026-05-27T02:05:09.903539+00:00","updated_at":"2026-05-27T02:05:09.903539+00:00"}