{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KMTRBALCFCEKTQ3AVWINVYQGOT","short_pith_number":"pith:KMTRBALC","schema_version":"1.0","canonical_sha256":"53271081622888a9c360ad90dae20674f15b14d23c7fe5d985f43aa0511e3080","source":{"kind":"arxiv","id":"2603.02943","version":2},"attestation_state":"computed","paper":{"title":"TC-Pad\\'e: Trajectory-Consistent Pad\\'e Approximation for Diffusion Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benlei Cui, Bukun Huang, Haiwen Hong, Hui Xue, Jingqun Tang, Longtao Huang, Shaoxuan He, Yang Yang, Yunyun Sun, Zhizeng Ye, Zhou Zhao","submitted_at":"2026-03-03T12:50:26Z","abstract_excerpt":"Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step counts (e.g., 50 steps), they exhibit critical limitations in the practical low-step regime of 20-30 steps. As the interval between steps increases, polynomial-based extrapolators like TaylorSeer suffer from error accumulation and trajectory drift. Meanwhile, conventional caching strategies often overlook the distinct dynamical properties of different denoi"},"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":"2603.02943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-03T12:50:26Z","cross_cats_sorted":[],"title_canon_sha256":"53fa009afa5653d648d3a5cd649089b17cabb9cba3b295aa2cbcdc31a7815d07","abstract_canon_sha256":"2cac8bf8619b9afbbb9017e569ec46d729efad175205ef6ca6ed3d34a2ccccb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:24:57.812942Z","signature_b64":"TWRnJnGWIC/Wjr2G8U05Bi7F7omExe4dbZsKuWMHy/xU8UnhR75F0BsuZAL7wRJ3kqyv74gpuVjxBUGLs5GeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53271081622888a9c360ad90dae20674f15b14d23c7fe5d985f43aa0511e3080","last_reissued_at":"2026-08-13T01:24:57.810544Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:24:57.810544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TC-Pad\\'e: Trajectory-Consistent Pad\\'e Approximation for Diffusion Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benlei Cui, Bukun Huang, Haiwen Hong, Hui Xue, Jingqun Tang, Longtao Huang, Shaoxuan He, Yang Yang, Yunyun Sun, Zhizeng Ye, Zhou Zhao","submitted_at":"2026-03-03T12:50:26Z","abstract_excerpt":"Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step counts (e.g., 50 steps), they exhibit critical limitations in the practical low-step regime of 20-30 steps. As the interval between steps increases, polynomial-based extrapolators like TaylorSeer suffer from error accumulation and trajectory drift. Meanwhile, conventional caching strategies often overlook the distinct dynamical properties of different denoi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.02943","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/2603.02943/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":"2603.02943","created_at":"2026-08-13T01:24:57.811715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.02943v2","created_at":"2026-08-13T01:24:57.811715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02943","created_at":"2026-08-13T01:24:57.811715+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMTRBALCFCEK","created_at":"2026-08-13T01:24:57.811715+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMTRBALCFCEKTQ3A","created_at":"2026-08-13T01:24:57.811715+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMTRBALC","created_at":"2026-08-13T01:24:57.811715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.25034","citing_title":"Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25034","citing_title":"Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18173","citing_title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03339","citing_title":"Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT","json":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT.json","graph_json":"https://pith.science/api/pith-number/KMTRBALCFCEKTQ3AVWINVYQGOT/graph.json","events_json":"https://pith.science/api/pith-number/KMTRBALCFCEKTQ3AVWINVYQGOT/events.json","paper":"https://pith.science/paper/KMTRBALC"},"agent_actions":{"view_html":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT","download_json":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT.json","view_paper":"https://pith.science/paper/KMTRBALC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.02943&json=true","fetch_graph":"https://pith.science/api/pith-number/KMTRBALCFCEKTQ3AVWINVYQGOT/graph.json","fetch_events":"https://pith.science/api/pith-number/KMTRBALCFCEKTQ3AVWINVYQGOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT/action/storage_attestation","attest_author":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT/action/author_attestation","sign_citation":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT/action/citation_signature","submit_replication":"https://pith.science/pith/KMTRBALCFCEKTQ3AVWINVYQGOT/action/replication_record"}},"created_at":"2026-08-13T01:24:57.811715+00:00","updated_at":"2026-08-13T01:24:57.811715+00:00"}