{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:32FFQ7FKLNADSOTAMEAJMKRYGX","short_pith_number":"pith:32FFQ7FK","canonical_record":{"source":{"id":"2605.06395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:08:58Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"ca2ca05275edf19b89e941cd92a1105e1b6c803cbd56ed08dec8975d70b41671","abstract_canon_sha256":"c62159cb5f3bb3fd1b2a466fbbf4d3c2f8a5d8fc25dce127fb02c7b2b66adbcb"},"schema_version":"1.0"},"canonical_sha256":"de8a587caa5b40393a606100962a3835f746f59f3fad37bf6a86a5c97cfca67d","source":{"kind":"arxiv","id":"2605.06395","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.06395","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.06395v2","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06395","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"32FFQ7FKLNAD","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"32FFQ7FKLNADSOTA","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"32FFQ7FK","created_at":"2026-05-21T01:04:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:32FFQ7FKLNADSOTAMEAJMKRYGX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.06395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:08:58Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"ca2ca05275edf19b89e941cd92a1105e1b6c803cbd56ed08dec8975d70b41671","abstract_canon_sha256":"c62159cb5f3bb3fd1b2a466fbbf4d3c2f8a5d8fc25dce127fb02c7b2b66adbcb"},"schema_version":"1.0"},"canonical_sha256":"de8a587caa5b40393a606100962a3835f746f59f3fad37bf6a86a5c97cfca67d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:26.974540Z","signature_b64":"XdrDI8uEbTJQNlaOgcBKh1owoTlwkhk0UGV0Yia834rukceF8onRB+5xYdIHUaSca2pgTPN2eEI7P6pBT8r2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de8a587caa5b40393a606100962a3835f746f59f3fad37bf6a86a5c97cfca67d","last_reissued_at":"2026-05-21T01:04:26.973934Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:26.973934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.06395","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":"2026-05-21T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uV7iyyTUIKyOOwMRAGge3NXnutTYT3xkpvbNvsyHK/OflN5Zkrq7UYoJul/Ekii/REMCb+Hpul45+UryWPk4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:15:08.270907Z"},"content_sha256":"747d2ef000d249a5b056d954b3e0942a45ab3e01ae9baa89da538bfc67d412a4","schema_version":"1.0","event_id":"sha256:747d2ef000d249a5b056d954b3e0942a45ab3e01ae9baa89da538bfc67d412a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:32FFQ7FKLNADSOTAMEAJMKRYGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals.","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Claudio Battiloro, Francesca Dominici, Julian Gould, Kartik Tandon, Tanishq Bhatia","submitted_at":"2026-05-07T15:08:58Z","abstract_excerpt":"Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operators, and are defined over irregular domains. Yet, a unified learning theory for these settings has been lacking. To start addressing this gap, we introduce a novel convolutional learning framework for possibly infinite-dimensional signals supported on a manifold. Namely, we use the connection Laplacian associated with a Hilbert bundle as a convolutional operator, and we derive filters and neural networks, dubbed as \\"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin & Niyogi convergence result for the graph Laplacian to the manifold Laplacian","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Sampling the manifold induces a Hilbert Cellular Sheaf with edge-wise coupling rules that preserve the necessary structure for the Laplacian convergence to hold in the infinite-dimensional Hilbert bundle case.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HilbNets discretize Hilbert bundle convolutions through Hilbert Cellular Sheaves whose Laplacians converge to the continuous connection Laplacian, enabling consistent learning across samplings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4e6ef27b4aad7372157746d0960500911638fc918797be271de245b945b6aa1d"},"source":{"id":"2605.06395","kind":"arxiv","version":2},"verdict":{"id":"fbfadf8f-521c-45af-8384-cba0bb58207b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T12:48:21.143336Z","strongest_claim":"we prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin & Niyogi convergence result for the graph Laplacian to the manifold Laplacian","one_line_summary":"HilbNets discretize Hilbert bundle convolutions through Hilbert Cellular Sheaves whose Laplacians converge to the continuous connection Laplacian, enabling consistent learning across samplings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Sampling the manifold induces a Hilbert Cellular Sheaf with edge-wise coupling rules that preserve the necessary structure for the Laplacian convergence to hold in the infinite-dimensional Hilbert bundle case.","pith_extraction_headline":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06395/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T12:42:03.970960Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T07:43:22.876064Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.164260Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:43:47.236347Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c8a7cdea3631ebace37fb1f2669590e3f825de61882be8178076bfd918fab78e"},"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":"fbfadf8f-521c-45af-8384-cba0bb58207b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wytW+LPKldSTz1bTU61kWPTXMztusTwUUHuAmE0KRodc3/yJodSg+K2TvGKyXkiMsP8yjOUL8ffmkoOi9STmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:15:08.271487Z"},"content_sha256":"0c462322c088f3120e7188a798da60e697cc324f0c0b1e79f5ba7c5324254873","schema_version":"1.0","event_id":"sha256:0c462322c088f3120e7188a798da60e697cc324f0c0b1e79f5ba7c5324254873"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/bundle.json","state_url":"https://pith.science/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/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":"2026-05-31T07:15:08Z","links":{"resolver":"https://pith.science/pith/32FFQ7FKLNADSOTAMEAJMKRYGX","bundle":"https://pith.science/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/bundle.json","state":"https://pith.science/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32FFQ7FKLNADSOTAMEAJMKRYGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:32FFQ7FKLNADSOTAMEAJMKRYGX","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":"c62159cb5f3bb3fd1b2a466fbbf4d3c2f8a5d8fc25dce127fb02c7b2b66adbcb","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:08:58Z","title_canon_sha256":"ca2ca05275edf19b89e941cd92a1105e1b6c803cbd56ed08dec8975d70b41671"},"schema_version":"1.0","source":{"id":"2605.06395","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.06395","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.06395v2","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06395","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"32FFQ7FKLNAD","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"32FFQ7FKLNADSOTA","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"32FFQ7FK","created_at":"2026-05-21T01:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:0c462322c088f3120e7188a798da60e697cc324f0c0b1e79f5ba7c5324254873","target":"graph","created_at":"2026-05-21T01:04:26Z","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 prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin & Niyogi convergence result for the graph Laplacian to the manifold Laplacian"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Sampling the manifold induces a Hilbert Cellular Sheaf with edge-wise coupling rules that preserve the necessary structure for the Laplacian convergence to hold in the infinite-dimensional Hilbert bundle case."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HilbNets discretize Hilbert bundle convolutions through Hilbert Cellular Sheaves whose Laplacians converge to the continuous connection Laplacian, enabling consistent learning across samplings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals."}],"snapshot_sha256":"4e6ef27b4aad7372157746d0960500911638fc918797be271de245b945b6aa1d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T12:42:03.970960Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T07:43:22.876064Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.164260Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T12:43:47.236347Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.06395/integrity.json","findings":[],"snapshot_sha256":"c8a7cdea3631ebace37fb1f2669590e3f825de61882be8178076bfd918fab78e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operators, and are defined over irregular domains. Yet, a unified learning theory for these settings has been lacking. To start addressing this gap, we introduce a novel convolutional learning framework for possibly infinite-dimensional signals supported on a manifold. Namely, we use the connection Laplacian associated with a Hilbert bundle as a convolutional operator, and we derive filters and neural networks, dubbed as \\","authors_text":"Alejandro Ribeiro, Claudio Battiloro, Francesca Dominici, Julian Gould, Kartik Tandon, Tanishq Bhatia","cross_cats":["cs.AI","eess.SP"],"headline":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:08:58Z","title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.06395","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T12:48:21.143336Z","id":"fbfadf8f-521c-45af-8384-cba0bb58207b","model_set":{"reader":"grok-4.3"},"one_line_summary":"HilbNets discretize Hilbert bundle convolutions through Hilbert Cellular Sheaves whose Laplacians converge to the continuous connection Laplacian, enabling consistent learning across samplings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sampling a manifold with a Hilbert bundle induces a cellular sheaf whose Laplacian converges in probability to the connection Laplacian, enabling consistent discrete networks for infinite-dimensional signals.","strongest_claim":"we prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin & Niyogi convergence result for the graph Laplacian to the manifold Laplacian","weakest_assumption":"Sampling the manifold induces a Hilbert Cellular Sheaf with edge-wise coupling rules that preserve the necessary structure for the Laplacian convergence to hold in the infinite-dimensional Hilbert bundle case."}},"verdict_id":"fbfadf8f-521c-45af-8384-cba0bb58207b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:747d2ef000d249a5b056d954b3e0942a45ab3e01ae9baa89da538bfc67d412a4","target":"record","created_at":"2026-05-21T01:04:26Z","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":"c62159cb5f3bb3fd1b2a466fbbf4d3c2f8a5d8fc25dce127fb02c7b2b66adbcb","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:08:58Z","title_canon_sha256":"ca2ca05275edf19b89e941cd92a1105e1b6c803cbd56ed08dec8975d70b41671"},"schema_version":"1.0","source":{"id":"2605.06395","kind":"arxiv","version":2}},"canonical_sha256":"de8a587caa5b40393a606100962a3835f746f59f3fad37bf6a86a5c97cfca67d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de8a587caa5b40393a606100962a3835f746f59f3fad37bf6a86a5c97cfca67d","first_computed_at":"2026-05-21T01:04:26.973934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:26.973934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdrDI8uEbTJQNlaOgcBKh1owoTlwkhk0UGV0Yia834rukceF8onRB+5xYdIHUaSca2pgTPN2eEI7P6pBT8r2DQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:26.974540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.06395","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:747d2ef000d249a5b056d954b3e0942a45ab3e01ae9baa89da538bfc67d412a4","sha256:0c462322c088f3120e7188a798da60e697cc324f0c0b1e79f5ba7c5324254873"],"state_sha256":"4fca11ec9e822d6155bc0b020d61d828c44e257941d8c239133ed7ef3b3b3a70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JwwZRbjyelI2ojP/2xOFyA4qXUBms/tLlpBOplrZ3xMCc2DJ335GxpwypUyNIA9DtWtY01Gj5tNQr5fRs89YBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:15:08.274311Z","bundle_sha256":"07a8cf53e79f0e67c86fd904f7c699446dae29ad38c1ca8dfc18c06ba0199c6c"}}