{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VXEFVHB2LJDSGBZB4WOHAQS4K6","short_pith_number":"pith:VXEFVHB2","canonical_record":{"source":{"id":"2410.04096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T09:33:39Z","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"title_canon_sha256":"c05a4f162b370416a01d238f7c13c9455a05821465a80f915db28c552f14e1a4","abstract_canon_sha256":"4a8c9fa76f7da6dc872356e6eda68253bd8f4caa25713827c283e7dfba694fee"},"schema_version":"1.0"},"canonical_sha256":"adc85a9c3a5a47230721e59c70425c57b80f4b85f73b96a883867bbdbebccf8e","source":{"kind":"arxiv","id":"2410.04096","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04096","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04096v2","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04096","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"VXEFVHB2LJDS","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"VXEFVHB2LJDSGBZB","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"VXEFVHB2","created_at":"2026-05-28T02:04:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VXEFVHB2LJDSGBZB4WOHAQS4K6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T09:33:39Z","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"title_canon_sha256":"c05a4f162b370416a01d238f7c13c9455a05821465a80f915db28c552f14e1a4","abstract_canon_sha256":"4a8c9fa76f7da6dc872356e6eda68253bd8f4caa25713827c283e7dfba694fee"},"schema_version":"1.0"},"canonical_sha256":"adc85a9c3a5a47230721e59c70425c57b80f4b85f73b96a883867bbdbebccf8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:39.194163Z","signature_b64":"gpMwTNJ+4zfxIo6iY8LCY5Y07ixJuaGnFZtu0vtWgq85dNPm9MWMWpztTZpOnbs7bcsmrnGwHQUDtp1/HBrFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc85a9c3a5a47230721e59c70425c57b80f4b85f73b96a883867bbdbebccf8e","last_reissued_at":"2026-05-28T02:04:39.193677Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:39.193677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04096","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5zOFWukRDr3DtMG2cfjFQq5cWzql70J++HhzyqShDwKVY2fdHmYCkFrq7h0ldyOcJRAlamSbQ8/yVDCvJ/YCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:24:19.251940Z"},"content_sha256":"c2573f3af71d51ca948d9d25d105a2b48331b8fe94db1c1c08d867c48053b042","schema_version":"1.0","event_id":"sha256:c2573f3af71d51ca948d9d25d105a2b48331b8fe94db1c1c08d867c48053b042"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VXEFVHB2LJDSGBZB4WOHAQS4K6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving.","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Ivan Oseledets, Jiang Yang, Jingwei Qiu, Tianchi Yu","submitted_at":"2024-10-05T09:33:39Z","abstract_excerpt":"In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation functions, which recently gained attention as alternatives to Multilayer Perceptron. Many different function representations have already been tried, but we show that Sinc interpolation proposes a viable alternative, since it is known in numerical analysis to effectively represent both smooth functions and functions with singularities. This is important not only for function approximation but also for solving the partial differential equations with physics"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Sinc interpolation can be directly substituted as the learnable activation basis inside the KAN framework while preserving the network's training dynamics and that the chosen experimental examples are representative of the target applications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SincKANs integrate Sinc interpolation into KAN activations and report better empirical results than alternatives on function approximation and PINN tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3d70f9c99f5ef54a8c964bbc0311d8e6e62c814fe9dcb1e9bd7e54e69bcac729"},"source":{"id":"2410.04096","kind":"arxiv","version":2},"verdict":{"id":"83e377b9-5ce9-462d-b057-bf2347992a7f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T19:40:19.228103Z","strongest_claim":"Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered.","one_line_summary":"SincKANs integrate Sinc interpolation into KAN activations and report better empirical results than alternatives on function approximation and PINN tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Sinc interpolation can be directly substituted as the learnable activation basis inside the KAN framework while preserving the network's training dynamics and that the chosen experimental examples are representative of the target applications.","pith_extraction_headline":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.04096/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"},"verdict_id":"83e377b9-5ce9-462d-b057-bf2347992a7f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJ2UKOJagyhAl5j/YtQtR2+0EQiHaU3bOh4TFr8KIMIiowPpETHlLPGXDX4eQOP/BzbKaUGAgl5lXL7VAs9aBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:24:19.252528Z"},"content_sha256":"6a75abfbcd0b40719b1d4294c0ff806f5693871c53d08c5e0791a86ea23b7f32","schema_version":"1.0","event_id":"sha256:6a75abfbcd0b40719b1d4294c0ff806f5693871c53d08c5e0791a86ea23b7f32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/bundle.json","state_url":"https://pith.science/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T06:24:19Z","links":{"resolver":"https://pith.science/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6","bundle":"https://pith.science/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/bundle.json","state":"https://pith.science/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXEFVHB2LJDSGBZB4WOHAQS4K6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VXEFVHB2LJDSGBZB4WOHAQS4K6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4a8c9fa76f7da6dc872356e6eda68253bd8f4caa25713827c283e7dfba694fee","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T09:33:39Z","title_canon_sha256":"c05a4f162b370416a01d238f7c13c9455a05821465a80f915db28c552f14e1a4"},"schema_version":"1.0","source":{"id":"2410.04096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04096","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04096v2","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04096","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"VXEFVHB2LJDS","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"VXEFVHB2LJDSGBZB","created_at":"2026-05-28T02:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"VXEFVHB2","created_at":"2026-05-28T02:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:6a75abfbcd0b40719b1d4294c0ff806f5693871c53d08c5e0791a86ea23b7f32","target":"graph","created_at":"2026-05-28T02:04:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That Sinc interpolation can be directly substituted as the learnable activation basis inside the KAN framework while preserving the network's training dynamics and that the chosen experimental examples are representative of the target applications."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SincKANs integrate Sinc interpolation into KAN activations and report better empirical results than alternatives on function approximation and PINN tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving."}],"snapshot_sha256":"3d70f9c99f5ef54a8c964bbc0311d8e6e62c814fe9dcb1e9bd7e54e69bcac729"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.04096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation functions, which recently gained attention as alternatives to Multilayer Perceptron. Many different function representations have already been tried, but we show that Sinc interpolation proposes a viable alternative, since it is known in numerical analysis to effectively represent both smooth functions and functions with singularities. This is important not only for function approximation but also for solving the partial differential equations with physics","authors_text":"Ivan Oseledets, Jiang Yang, Jingwei Qiu, Tianchi Yu","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"headline":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T09:33:39Z","title":"Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04096","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-23T19:40:19.228103Z","id":"83e377b9-5ce9-462d-b057-bf2347992a7f","model_set":{"reader":"grok-4.3"},"one_line_summary":"SincKANs integrate Sinc interpolation into KAN activations and report better empirical results than alternatives on function approximation and PINN tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sinc interpolation serves as an effective learnable activation basis in Kolmogorov-Arnold Networks for function approximation and PDE solving.","strongest_claim":"Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered.","weakest_assumption":"That Sinc interpolation can be directly substituted as the learnable activation basis inside the KAN framework while preserving the network's training dynamics and that the chosen experimental examples are representative of the target applications."}},"verdict_id":"83e377b9-5ce9-462d-b057-bf2347992a7f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2573f3af71d51ca948d9d25d105a2b48331b8fe94db1c1c08d867c48053b042","target":"record","created_at":"2026-05-28T02:04:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4a8c9fa76f7da6dc872356e6eda68253bd8f4caa25713827c283e7dfba694fee","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T09:33:39Z","title_canon_sha256":"c05a4f162b370416a01d238f7c13c9455a05821465a80f915db28c552f14e1a4"},"schema_version":"1.0","source":{"id":"2410.04096","kind":"arxiv","version":2}},"canonical_sha256":"adc85a9c3a5a47230721e59c70425c57b80f4b85f73b96a883867bbdbebccf8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adc85a9c3a5a47230721e59c70425c57b80f4b85f73b96a883867bbdbebccf8e","first_computed_at":"2026-05-28T02:04:39.193677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:39.193677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gpMwTNJ+4zfxIo6iY8LCY5Y07ixJuaGnFZtu0vtWgq85dNPm9MWMWpztTZpOnbs7bcsmrnGwHQUDtp1/HBrFCA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:39.194163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2573f3af71d51ca948d9d25d105a2b48331b8fe94db1c1c08d867c48053b042","sha256:6a75abfbcd0b40719b1d4294c0ff806f5693871c53d08c5e0791a86ea23b7f32"],"state_sha256":"77dccb37921eabcf0bf72a5b9260c298f7521aa771c387817ad373b84e12509e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNWoVSz7VtUIU6JcC41GmSZffhhlJX4NtTfzAvDO1GWd/QBlC1EksLJ+jld76MHiFGy6t5mD/CaxPTZu0D2ODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:24:19.256134Z","bundle_sha256":"dd360d892495b273e232de5f7bf0d97b27bd43ee62ccd602fd4db75a617458f9"}}