{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2K55LQQHOU3QKKEIV2CEY6ZPUC","short_pith_number":"pith:2K55LQQH","canonical_record":{"source":{"id":"2512.19184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-22T09:18:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d8212e93db9d60261d54420ea324f42323c622efa1f1d9057837b60c48bc100","abstract_canon_sha256":"9aea679f4fc4dd2234aa90829eab2aea16e91dbe13518c968ad75ec0a782bda9"},"schema_version":"1.0"},"canonical_sha256":"d2bbd5c2077537052888ae844c7b2fa098bad41b6c50c191887f91a1105c1e76","source":{"kind":"arxiv","id":"2512.19184","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.19184","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2512.19184v2","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.19184","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"2K55LQQHOU3Q","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"2K55LQQHOU3QKKEI","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"2K55LQQH","created_at":"2026-05-25T02:02:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2K55LQQHOU3QKKEIV2CEY6ZPUC","target":"record","payload":{"canonical_record":{"source":{"id":"2512.19184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-22T09:18:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d8212e93db9d60261d54420ea324f42323c622efa1f1d9057837b60c48bc100","abstract_canon_sha256":"9aea679f4fc4dd2234aa90829eab2aea16e91dbe13518c968ad75ec0a782bda9"},"schema_version":"1.0"},"canonical_sha256":"d2bbd5c2077537052888ae844c7b2fa098bad41b6c50c191887f91a1105c1e76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:11.712623Z","signature_b64":"rDaZETyc+Hk5+iXYBvM3ZZNmI6nyKFx/mFH6UKfDpE+PyFkgYFKtualda0BvUgXeRD1cIF4ACUqqTvrCPEZ5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2bbd5c2077537052888ae844c7b2fa098bad41b6c50c191887f91a1105c1e76","last_reissued_at":"2026-05-25T02:02:11.711870Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:11.711870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.19184","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":"2026-05-25T02:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpeUdr9GNHJeuCbU+aBGndsNckXlQZUzNDY8NS6PwOnBNbEZ3Ag84ARY2Xi5z1HMhRRGaw4GdeWOle0CZpbEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:30:38.684686Z"},"content_sha256":"8c76197b94beeb47dd56f4eb859cf9fe32af95709338c8e2b873f005cad93e29","schema_version":"1.0","event_id":"sha256:8c76197b94beeb47dd56f4eb859cf9fe32af95709338c8e2b873f005cad93e29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2K55LQQHOU3QKKEIV2CEY6ZPUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Operator-Based Generalization Bound for Deep Learning: Insights on Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Giuseppe Di Fatta, Giuseppe Nicosia, Mahdi Mohammadigohari, Panos M. Pardalos","submitted_at":"2025-12-22T09:18:30Z","abstract_excerpt":"This paper presents novel generalization bounds for vector-valued neural networks and deep kernel methods, focusing on multi-task learning through an operator-theoretic framework. Our key development lies in strategically combining a Koopman based approach with existing techniques, achieving tighter generalization guarantees compared to traditional norm-based bounds. To mitigate computational challenges associated with Koopman-based methods, we introduce sketching techniques applicable to vector valued neural networks. These techniques yield excess risk bounds under generic Lipschitz losses, p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.19184","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/2512.19184/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":"2026-05-25T02:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bN+FhkuJMMTf5ZwnApG9c4l/uDVmW/R4ap6t3UCyA1x4OLKq8+f9M48xdb5fQxPitfb1Sar8XEwuF/uLBhbsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:30:38.685173Z"},"content_sha256":"c5673315973afbb3a37263b6d1dd10405c1ac9b01aea2e15ad7d72f97ceee11c","schema_version":"1.0","event_id":"sha256:c5673315973afbb3a37263b6d1dd10405c1ac9b01aea2e15ad7d72f97ceee11c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/bundle.json","state_url":"https://pith.science/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/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":"2026-05-27T08:30:38Z","links":{"resolver":"https://pith.science/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC","bundle":"https://pith.science/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/bundle.json","state":"https://pith.science/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2K55LQQHOU3QKKEIV2CEY6ZPUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2K55LQQHOU3QKKEIV2CEY6ZPUC","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":"9aea679f4fc4dd2234aa90829eab2aea16e91dbe13518c968ad75ec0a782bda9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-22T09:18:30Z","title_canon_sha256":"7d8212e93db9d60261d54420ea324f42323c622efa1f1d9057837b60c48bc100"},"schema_version":"1.0","source":{"id":"2512.19184","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.19184","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2512.19184v2","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.19184","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"2K55LQQHOU3Q","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"2K55LQQHOU3QKKEI","created_at":"2026-05-25T02:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"2K55LQQH","created_at":"2026-05-25T02:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:c5673315973afbb3a37263b6d1dd10405c1ac9b01aea2e15ad7d72f97ceee11c","target":"graph","created_at":"2026-05-25T02:02:11Z","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/2512.19184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents novel generalization bounds for vector-valued neural networks and deep kernel methods, focusing on multi-task learning through an operator-theoretic framework. Our key development lies in strategically combining a Koopman based approach with existing techniques, achieving tighter generalization guarantees compared to traditional norm-based bounds. To mitigate computational challenges associated with Koopman-based methods, we introduce sketching techniques applicable to vector valued neural networks. These techniques yield excess risk bounds under generic Lipschitz losses, p","authors_text":"Giuseppe Di Fatta, Giuseppe Nicosia, Mahdi Mohammadigohari, Panos M. Pardalos","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-22T09:18:30Z","title":"Operator-Based Generalization Bound for Deep Learning: Insights on Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.19184","kind":"arxiv","version":2},"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":"sha256:8c76197b94beeb47dd56f4eb859cf9fe32af95709338c8e2b873f005cad93e29","target":"record","created_at":"2026-05-25T02:02:11Z","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":"9aea679f4fc4dd2234aa90829eab2aea16e91dbe13518c968ad75ec0a782bda9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-22T09:18:30Z","title_canon_sha256":"7d8212e93db9d60261d54420ea324f42323c622efa1f1d9057837b60c48bc100"},"schema_version":"1.0","source":{"id":"2512.19184","kind":"arxiv","version":2}},"canonical_sha256":"d2bbd5c2077537052888ae844c7b2fa098bad41b6c50c191887f91a1105c1e76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2bbd5c2077537052888ae844c7b2fa098bad41b6c50c191887f91a1105c1e76","first_computed_at":"2026-05-25T02:02:11.711870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:11.711870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDaZETyc+Hk5+iXYBvM3ZZNmI6nyKFx/mFH6UKfDpE+PyFkgYFKtualda0BvUgXeRD1cIF4ACUqqTvrCPEZ5AQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:11.712623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.19184","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c76197b94beeb47dd56f4eb859cf9fe32af95709338c8e2b873f005cad93e29","sha256:c5673315973afbb3a37263b6d1dd10405c1ac9b01aea2e15ad7d72f97ceee11c"],"state_sha256":"e0cb558d14879afe3d3fdabdbbb1894a91bad3fec9585dd9bd8b15ebed309310"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmugXvvFpZVpH4sKUUOtrqAS9qpIKaxwU0LTzUZRE2rf0+57r1FbOGG6UngwwAuowOvD/RNsHI0YdHZRID+PCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T08:30:38.687547Z","bundle_sha256":"6c1079016b5c9aa2d461ac62457a37b5d49db8675bb9dcb065381e1bdb4db288"}}