{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7CAVBZV4LBGCFV3KWPEOXRQZ45","short_pith_number":"pith:7CAVBZV4","schema_version":"1.0","canonical_sha256":"f88150e6bc584c22d76ab3c8ebc619e77782f78267a71f9e3fd15c841d43f921","source":{"kind":"arxiv","id":"2502.19754","version":2},"attestation_state":"computed","paper":{"title":"Finding Local Diffusion Schr\\\"odinger Bridge using Kolmogorov-Arnold Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Liang, Fanding Li, Gongning Luo, Kuanquan Wang, Mengying Yang, Shuo Li, Wei Wang, Xinghua Ma, Xingyu Qiu","submitted_at":"2025-02-27T04:34:03Z","abstract_excerpt":"In image generation, Schr\\\"odinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path between two distributions. However, they are computationally expensive and time-consuming when applied to complex image data. The reason is that they focus on fitting globally optimal paths in high-dimensional spaces, directly generating images as next step on the path using complex networks through self-supervised training, which typically results in a gap with the global optimum. Meanwhile, most diffusion models are 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":"2502.19754","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T04:34:03Z","cross_cats_sorted":[],"title_canon_sha256":"db9891db53d9561e5a79e1ca718604c4f50c07f38a249f07f1983cb9cd11a92c","abstract_canon_sha256":"52be98eb7fafe7887bba3f77e0e88c8fe9e63076ecaf8f353879f9da07927d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:30.194931Z","signature_b64":"aWxFelnRdchfUAe0LqQOHzgVSrj0/Td8UCjFAzN9QUzVZpZYVArKCY3apnIywZq49tmEd9J+QXiMwRASOYLhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f88150e6bc584c22d76ab3c8ebc619e77782f78267a71f9e3fd15c841d43f921","last_reissued_at":"2026-07-05T10:23:30.194138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:30.194138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Local Diffusion Schr\\\"odinger Bridge using Kolmogorov-Arnold Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Liang, Fanding Li, Gongning Luo, Kuanquan Wang, Mengying Yang, Shuo Li, Wei Wang, Xinghua Ma, Xingyu Qiu","submitted_at":"2025-02-27T04:34:03Z","abstract_excerpt":"In image generation, Schr\\\"odinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path between two distributions. However, they are computationally expensive and time-consuming when applied to complex image data. The reason is that they focus on fitting globally optimal paths in high-dimensional spaces, directly generating images as next step on the path using complex networks through self-supervised training, which typically results in a gap with the global optimum. Meanwhile, most diffusion models are in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19754","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/2502.19754/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":"2502.19754","created_at":"2026-07-05T10:23:30.194252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19754v2","created_at":"2026-07-05T10:23:30.194252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19754","created_at":"2026-07-05T10:23:30.194252+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CAVBZV4LBGC","created_at":"2026-07-05T10:23:30.194252+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CAVBZV4LBGCFV3K","created_at":"2026-07-05T10:23:30.194252+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CAVBZV4","created_at":"2026-07-05T10:23:30.194252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07549","citing_title":"Improving Memory Efficiency for Training KANs via Meta Learning","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45","json":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45.json","graph_json":"https://pith.science/api/pith-number/7CAVBZV4LBGCFV3KWPEOXRQZ45/graph.json","events_json":"https://pith.science/api/pith-number/7CAVBZV4LBGCFV3KWPEOXRQZ45/events.json","paper":"https://pith.science/paper/7CAVBZV4"},"agent_actions":{"view_html":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45","download_json":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45.json","view_paper":"https://pith.science/paper/7CAVBZV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19754&json=true","fetch_graph":"https://pith.science/api/pith-number/7CAVBZV4LBGCFV3KWPEOXRQZ45/graph.json","fetch_events":"https://pith.science/api/pith-number/7CAVBZV4LBGCFV3KWPEOXRQZ45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45/action/storage_attestation","attest_author":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45/action/author_attestation","sign_citation":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45/action/citation_signature","submit_replication":"https://pith.science/pith/7CAVBZV4LBGCFV3KWPEOXRQZ45/action/replication_record"}},"created_at":"2026-07-05T10:23:30.194252+00:00","updated_at":"2026-07-05T10:23:30.194252+00:00"}