{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXXJOD7K5JYQENVSAVYZH5IC5E","short_pith_number":"pith:EXXJOD7K","canonical_record":{"source":{"id":"2605.24584","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T13:48:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed8bce1061e4f9d0cf1526c20e5ada7c1d6bc4ea17f0cb0282b6f6e34f88e34b","abstract_canon_sha256":"1071b6048e292d606ee5eced3ba2b471cb1a3b3b7618bbad51ff1436ff9e8e5e"},"schema_version":"1.0"},"canonical_sha256":"25ee970feaea710236b2057193f502e921c144a66abcf69f3cf9b3157c95a1d2","source":{"kind":"arxiv","id":"2605.24584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24584","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24584v1","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24584","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"EXXJOD7K5JYQ","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"EXXJOD7K5JYQENVS","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"EXXJOD7K","created_at":"2026-05-26T01:03:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXXJOD7K5JYQENVSAVYZH5IC5E","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24584","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T13:48:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed8bce1061e4f9d0cf1526c20e5ada7c1d6bc4ea17f0cb0282b6f6e34f88e34b","abstract_canon_sha256":"1071b6048e292d606ee5eced3ba2b471cb1a3b3b7618bbad51ff1436ff9e8e5e"},"schema_version":"1.0"},"canonical_sha256":"25ee970feaea710236b2057193f502e921c144a66abcf69f3cf9b3157c95a1d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:47.514504Z","signature_b64":"e8YhDTu7GmJtLBq97t/g/p4wWuLIiwmeCrwtjKqktFz6owyaUpsE/S1rv9dMsBfqK7rPRZAbND6JHtmeYlWuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ee970feaea710236b2057193f502e921c144a66abcf69f3cf9b3157c95a1d2","last_reissued_at":"2026-05-26T01:03:47.513674Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:47.513674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24584","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0KC6s12tptLdpyERv26CuiJ0mRDZnFtUpu59IaIP7gKPB7Od9lF1lNnjQvGJkzZ2+06XFPQ40eewEYsEq1HtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:05:23.080432Z"},"content_sha256":"229d1c910434f1cefa3150d8b53c0ce3ea656467cfc82b13b3b4df04c5230b2f","schema_version":"1.0","event_id":"sha256:229d1c910434f1cefa3150d8b53c0ce3ea656467cfc82b13b3b4df04c5230b2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXXJOD7K5JYQENVSAVYZH5IC5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAPLEX: The FFT of Learnable Laplace Kernels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanna Blazhko, Jacek Tabor, {\\L}ukasz Struski, Piotr Kubaty","submitted_at":"2026-05-23T13:48:33Z","abstract_excerpt":"Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators.\n  A LAPLEX layer is a typically full-rank dense matrix, implicitly defined by learnable coordinate anchors, with FFT-like scaling. Consequently, it supports trainable matrix--vector operations at vector dimensions up to $10^9$ on modern GPUs. As a neural layer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24584","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/2605.24584/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RTWFiMR/B1ehd8yyefWfNCVwWE5h6keHQvnCJDuwSCM2E75yk1lN+sXp1FjapAzJ2nqy3Zdr7Cse1RTSijj7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:05:23.080845Z"},"content_sha256":"71f5c90bddf562a7fbe7676a6881bc8fdba883cbe3b9667a60b67354da445ce5","schema_version":"1.0","event_id":"sha256:71f5c90bddf562a7fbe7676a6881bc8fdba883cbe3b9667a60b67354da445ce5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/bundle.json","state_url":"https://pith.science/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/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":"2026-06-09T08:05:23Z","links":{"resolver":"https://pith.science/pith/EXXJOD7K5JYQENVSAVYZH5IC5E","bundle":"https://pith.science/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/bundle.json","state":"https://pith.science/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXXJOD7K5JYQENVSAVYZH5IC5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXXJOD7K5JYQENVSAVYZH5IC5E","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":"1071b6048e292d606ee5eced3ba2b471cb1a3b3b7618bbad51ff1436ff9e8e5e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T13:48:33Z","title_canon_sha256":"ed8bce1061e4f9d0cf1526c20e5ada7c1d6bc4ea17f0cb0282b6f6e34f88e34b"},"schema_version":"1.0","source":{"id":"2605.24584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24584","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24584v1","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24584","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"EXXJOD7K5JYQ","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"EXXJOD7K5JYQENVS","created_at":"2026-05-26T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"EXXJOD7K","created_at":"2026-05-26T01:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:71f5c90bddf562a7fbe7676a6881bc8fdba883cbe3b9667a60b67354da445ce5","target":"graph","created_at":"2026-05-26T01:03:47Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.24584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators.\n  A LAPLEX layer is a typically full-rank dense matrix, implicitly defined by learnable coordinate anchors, with FFT-like scaling. Consequently, it supports trainable matrix--vector operations at vector dimensions up to $10^9$ on modern GPUs. As a neural layer","authors_text":"Hanna Blazhko, Jacek Tabor, {\\L}ukasz Struski, Piotr Kubaty","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T13:48:33Z","title":"LAPLEX: The FFT of Learnable Laplace Kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24584","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:229d1c910434f1cefa3150d8b53c0ce3ea656467cfc82b13b3b4df04c5230b2f","target":"record","created_at":"2026-05-26T01:03:47Z","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":"1071b6048e292d606ee5eced3ba2b471cb1a3b3b7618bbad51ff1436ff9e8e5e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T13:48:33Z","title_canon_sha256":"ed8bce1061e4f9d0cf1526c20e5ada7c1d6bc4ea17f0cb0282b6f6e34f88e34b"},"schema_version":"1.0","source":{"id":"2605.24584","kind":"arxiv","version":1}},"canonical_sha256":"25ee970feaea710236b2057193f502e921c144a66abcf69f3cf9b3157c95a1d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ee970feaea710236b2057193f502e921c144a66abcf69f3cf9b3157c95a1d2","first_computed_at":"2026-05-26T01:03:47.513674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:47.513674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e8YhDTu7GmJtLBq97t/g/p4wWuLIiwmeCrwtjKqktFz6owyaUpsE/S1rv9dMsBfqK7rPRZAbND6JHtmeYlWuBA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:47.514504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:229d1c910434f1cefa3150d8b53c0ce3ea656467cfc82b13b3b4df04c5230b2f","sha256:71f5c90bddf562a7fbe7676a6881bc8fdba883cbe3b9667a60b67354da445ce5"],"state_sha256":"5bdc80e5e3ec0c65b9e6e784201cd370af3a62bec5b8286fe1a41d07e6663bb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PFvQL2a5rWpXWgASOXJol9P4frtfciVJu1igBRV542MMvuywTToZdGHS9K2ELiGRkDPY8UJJpVD3EyIh4UwuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:05:23.083131Z","bundle_sha256":"4de788a38ce24b32e637ecbdd84cfa0bb9d8129f03548a1e0d3fcf7593018746"}}