{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VDSUBEEG553OQFM2TYCDXDT6Q5","short_pith_number":"pith:VDSUBEEG","canonical_record":{"source":{"id":"2605.15524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:44:31Z","cross_cats_sorted":["cs.AI","math.DG","math.ST","stat.TH"],"title_canon_sha256":"1b53ccf7bc06c20ccd63b3fe6d60025f765de79c5fc13f1d6c0e8f9f175648b9","abstract_canon_sha256":"9a6f0e73ef6f02df1ed8e331a11b4649b4cb3bdc9796823f6351f6dc1eade060"},"schema_version":"1.0"},"canonical_sha256":"a8e5409086ef76e8159a9e043b8e7e87677df9e8ac70248b6a95bf67386f3a04","source":{"kind":"arxiv","id":"2605.15524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15524","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15524v1","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15524","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_12","alias_value":"VDSUBEEG553O","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_16","alias_value":"VDSUBEEG553OQFM2","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_8","alias_value":"VDSUBEEG","created_at":"2026-05-20T00:01:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VDSUBEEG553OQFM2TYCDXDT6Q5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:44:31Z","cross_cats_sorted":["cs.AI","math.DG","math.ST","stat.TH"],"title_canon_sha256":"1b53ccf7bc06c20ccd63b3fe6d60025f765de79c5fc13f1d6c0e8f9f175648b9","abstract_canon_sha256":"9a6f0e73ef6f02df1ed8e331a11b4649b4cb3bdc9796823f6351f6dc1eade060"},"schema_version":"1.0"},"canonical_sha256":"a8e5409086ef76e8159a9e043b8e7e87677df9e8ac70248b6a95bf67386f3a04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:03.223057Z","signature_b64":"7tN28+ZDcnakjSoK3fpVYx7Bt2TBczUe/tIy5SQIl45Nrxn/vGaVZhUaw9wG5orf2wFOjpOwGRHhX0r5Z+9XAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e5409086ef76e8159a9e043b8e7e87677df9e8ac70248b6a95bf67386f3a04","last_reissued_at":"2026-05-20T00:01:03.222127Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:03.222127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15524","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":"2026-05-20T00:01:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XxXGJbWj1ONwi8drpwvMgTWynHI4sdLuJIOS8XF5bVeKYlgUoZvdDf2XFVdwbPsMxdxZA6DM+i2O8tnZIvIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:33:58.853466Z"},"content_sha256":"75642425766e501445a3c1e8bce4ef35e85826790d15fa30c350c273c934c058","schema_version":"1.0","event_id":"sha256:75642425766e501445a3c1e8bce4ef35e85826790d15fa30c350c273c934c058"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VDSUBEEG553OQFM2TYCDXDT6Q5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Point-Forms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural point-forms represent point clouds as learned comparison matrices of differential forms.","cross_cats":["cs.AI","math.DG","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Bruno Trentini, Ekaterina S. Ivshina, Jacob Hume, Kelly Maggs, Philipp Misof, Vincenzo Antonio Isoldi","submitted_at":"2026-05-15T01:44:31Z","abstract_excerpt":"Point cloud learning often rests on the premise that observed samples are noisy traces of an underlying geometric object, such as a manifold embedded in a high-dimensional feature space. Yet much of this geometry is not captured directly by coordinates, pairwise distances, or learned graph neighborhoods alone. In the smooth setting, differential forms are devices to encode higher order tangency information. In this work, we introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). In the absence of a natural tangency structure, we inst"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). [...] We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The long-run consistency of comparison matrices holds under standard sampling, bandwidth, density, and manifold-hypothesis assumptions, as invoked to justify the theoretical foundation for the neural layer.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural point-forms represent point clouds as learned comparison matrices of differential forms.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d4dd03a98cddf12b86fd7a082896bf86ed2d935e00af705394feca8b01895b50"},"source":{"id":"2605.15524","kind":"arxiv","version":1},"verdict":{"id":"ebc32a8e-8b7d-49e1-9c33-0acaad451a70","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T14:53:28.984988Z","strongest_claim":"We introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). [...] We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix.","one_line_summary":"Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The long-run consistency of comparison matrices holds under standard sampling, bandwidth, density, and manifold-hypothesis assumptions, as invoked to justify the theoretical foundation for the neural layer.","pith_extraction_headline":"Neural point-forms represent point clouds as learned comparison matrices of differential forms."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15524/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T15:10:43.341455Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.541651Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T14:22:02.832334Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.043599Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.840525Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.377761Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.625908Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d6ba96b7377c78641234ab014f1ca2309e57485c72e0b75dded698466d0f3857"},"references":{"count":106,"sample":[{"doi":"","year":2021,"title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","work_id":"5e909969-dcfb-40f6-9099-241ea6f18350","ref_index":1,"cited_arxiv_id":"2104.13478","is_internal_anchor":true},{"doi":"","year":2017,"title":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. Neural message passing for quantum chemistry. InICML, 2017","work_id":"3e34c6f5-d742-43b5-9ec8-83e97b14a6e2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Relational inductive biases, deep learning, and graph networks","work_id":"858410c0-7a66-4b27-b4e5-49aee9725be0","ref_index":3,"cited_arxiv_id":"1806.01261","is_internal_anchor":true},{"doi":"","year":null,"title":"Hamilton, Rex Ying, and Jure Leskovec","work_id":"71ce6d22-412b-40ed-9123-7b3e082e6076","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Inductive Representation Learning on Large Graphs","work_id":"a84007af-8130-4a77-b631-738c9af563fd","ref_index":5,"cited_arxiv_id":"1706.02216","is_internal_anchor":true}],"resolved_work":106,"snapshot_sha256":"4c71a2ea84a66497fa6d713dd25ff67eb9231e797b75159285e586cb48e56755","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"67218b6c4b9b34cf772c2226225fa90437f737ccb996864a08d95519acc5633f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ebc32a8e-8b7d-49e1-9c33-0acaad451a70"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNqVWq1ULmmMVTLhtGpve158oHDHeFU3wtcyrYNZRh4hfHFlLVgRRCrt+Wpdd5jGQHuRKynwrpb9aX2DgzgJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:33:58.854106Z"},"content_sha256":"7beee2f7dd57153c2398812f6aee80de8b96b920fa11b0b947ba6112d91f58ac","schema_version":"1.0","event_id":"sha256:7beee2f7dd57153c2398812f6aee80de8b96b920fa11b0b947ba6112d91f58ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/bundle.json","state_url":"https://pith.science/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/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":"2026-05-21T09:33:58Z","links":{"resolver":"https://pith.science/pith/VDSUBEEG553OQFM2TYCDXDT6Q5","bundle":"https://pith.science/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/bundle.json","state":"https://pith.science/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDSUBEEG553OQFM2TYCDXDT6Q5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VDSUBEEG553OQFM2TYCDXDT6Q5","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":"9a6f0e73ef6f02df1ed8e331a11b4649b4cb3bdc9796823f6351f6dc1eade060","cross_cats_sorted":["cs.AI","math.DG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:44:31Z","title_canon_sha256":"1b53ccf7bc06c20ccd63b3fe6d60025f765de79c5fc13f1d6c0e8f9f175648b9"},"schema_version":"1.0","source":{"id":"2605.15524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15524","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15524v1","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15524","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_12","alias_value":"VDSUBEEG553O","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_16","alias_value":"VDSUBEEG553OQFM2","created_at":"2026-05-20T00:01:03Z"},{"alias_kind":"pith_short_8","alias_value":"VDSUBEEG","created_at":"2026-05-20T00:01:03Z"}],"graph_snapshots":[{"event_id":"sha256:7beee2f7dd57153c2398812f6aee80de8b96b920fa11b0b947ba6112d91f58ac","target":"graph","created_at":"2026-05-20T00:01:03Z","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":"We introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). [...] We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The long-run consistency of comparison matrices holds under standard sampling, bandwidth, density, and manifold-hypothesis assumptions, as invoked to justify the theoretical foundation for the neural layer."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Neural point-forms represent point clouds as learned comparison matrices of differential forms."}],"snapshot_sha256":"d4dd03a98cddf12b86fd7a082896bf86ed2d935e00af705394feca8b01895b50"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"67218b6c4b9b34cf772c2226225fa90437f737ccb996864a08d95519acc5633f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:10:43.341455Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.541651Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T14:22:02.832334Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.043599Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.840525Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.377761Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.625908Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15524/integrity.json","findings":[],"snapshot_sha256":"d6ba96b7377c78641234ab014f1ca2309e57485c72e0b75dded698466d0f3857","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Point cloud learning often rests on the premise that observed samples are noisy traces of an underlying geometric object, such as a manifold embedded in a high-dimensional feature space. Yet much of this geometry is not captured directly by coordinates, pairwise distances, or learned graph neighborhoods alone. In the smooth setting, differential forms are devices to encode higher order tangency information. In this work, we introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). In the absence of a natural tangency structure, we inst","authors_text":"Bruno Trentini, Ekaterina S. Ivshina, Jacob Hume, Kelly Maggs, Philipp Misof, Vincenzo Antonio Isoldi","cross_cats":["cs.AI","math.DG","math.ST","stat.TH"],"headline":"Neural point-forms represent point clouds as learned comparison matrices of differential forms.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:44:31Z","title":"Neural Point-Forms"},"references":{"count":106,"internal_anchors":7,"resolved_work":106,"sample":[{"cited_arxiv_id":"2104.13478","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","work_id":"5e909969-dcfb-40f6-9099-241ea6f18350","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. Neural message passing for quantum chemistry. InICML, 2017","work_id":"3e34c6f5-d742-43b5-9ec8-83e97b14a6e2","year":2017},{"cited_arxiv_id":"1806.01261","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Relational inductive biases, deep learning, and graph networks","work_id":"858410c0-7a66-4b27-b4e5-49aee9725be0","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Hamilton, Rex Ying, and Jure Leskovec","work_id":"71ce6d22-412b-40ed-9123-7b3e082e6076","year":null},{"cited_arxiv_id":"1706.02216","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Inductive Representation Learning on Large Graphs","work_id":"a84007af-8130-4a77-b631-738c9af563fd","year":null}],"snapshot_sha256":"4c71a2ea84a66497fa6d713dd25ff67eb9231e797b75159285e586cb48e56755"},"source":{"id":"2605.15524","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T14:53:28.984988Z","id":"ebc32a8e-8b7d-49e1-9c33-0acaad451a70","model_set":{"reader":"grok-4.3"},"one_line_summary":"Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Neural point-forms represent point clouds as learned comparison matrices of differential forms.","strongest_claim":"We introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). [...] We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix.","weakest_assumption":"The long-run consistency of comparison matrices holds under standard sampling, bandwidth, density, and manifold-hypothesis assumptions, as invoked to justify the theoretical foundation for the neural layer."}},"verdict_id":"ebc32a8e-8b7d-49e1-9c33-0acaad451a70"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:75642425766e501445a3c1e8bce4ef35e85826790d15fa30c350c273c934c058","target":"record","created_at":"2026-05-20T00:01:03Z","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":"9a6f0e73ef6f02df1ed8e331a11b4649b4cb3bdc9796823f6351f6dc1eade060","cross_cats_sorted":["cs.AI","math.DG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:44:31Z","title_canon_sha256":"1b53ccf7bc06c20ccd63b3fe6d60025f765de79c5fc13f1d6c0e8f9f175648b9"},"schema_version":"1.0","source":{"id":"2605.15524","kind":"arxiv","version":1}},"canonical_sha256":"a8e5409086ef76e8159a9e043b8e7e87677df9e8ac70248b6a95bf67386f3a04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8e5409086ef76e8159a9e043b8e7e87677df9e8ac70248b6a95bf67386f3a04","first_computed_at":"2026-05-20T00:01:03.222127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:03.222127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7tN28+ZDcnakjSoK3fpVYx7Bt2TBczUe/tIy5SQIl45Nrxn/vGaVZhUaw9wG5orf2wFOjpOwGRHhX0r5Z+9XAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:03.223057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75642425766e501445a3c1e8bce4ef35e85826790d15fa30c350c273c934c058","sha256:7beee2f7dd57153c2398812f6aee80de8b96b920fa11b0b947ba6112d91f58ac"],"state_sha256":"5f870aec569f91f6abc4709df1905d47f9262e734bbd3d73d856124027dd69f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPU1cyrvMOAv8mOw6zmO5cznrrnG/VFr/YUQ0fLT3DrfYB+htHKJrb5BQQSRQahVtcMjncFxcLeJEkKKs+8nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:33:58.857011Z","bundle_sha256":"a28182748bd5c3f1fdd773a160205910c7d1e99d81f7bad50f86160b94cd8c36"}}