{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:47T7FI4QI2H56TLPPO7J3QWEKG","short_pith_number":"pith:47T7FI4Q","canonical_record":{"source":{"id":"2501.12554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T00:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"5a0949eef4a6c2d6fb3f4871506e22452f3642c2ae6593d0e4fd6bc9d55346d3","abstract_canon_sha256":"d1281a55e71b4380ed9229ff46f608071119e51c07c7cde8c8eed3bb3e28ef6c"},"schema_version":"1.0"},"canonical_sha256":"e7e7f2a390468fdf4d6f7bbe9dc2c4518708b5059ed556271ccd4a25c88df066","source":{"kind":"arxiv","id":"2501.12554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12554","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12554v2","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12554","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"47T7FI4QI2H5","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"47T7FI4QI2H56TLP","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"47T7FI4Q","created_at":"2026-07-05T10:05:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:47T7FI4QI2H56TLPPO7J3QWEKG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T00:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"5a0949eef4a6c2d6fb3f4871506e22452f3642c2ae6593d0e4fd6bc9d55346d3","abstract_canon_sha256":"d1281a55e71b4380ed9229ff46f608071119e51c07c7cde8c8eed3bb3e28ef6c"},"schema_version":"1.0"},"canonical_sha256":"e7e7f2a390468fdf4d6f7bbe9dc2c4518708b5059ed556271ccd4a25c88df066","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:16.967139Z","signature_b64":"kXoTCZTGnBhDY8VNY43EwfQZW+Rn09JmwmndUKtY/XMIc06uhiBpMyKgQYVdTyMH6BuwunQnZLOC+HjDBIruCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e7f2a390468fdf4d6f7bbe9dc2c4518708b5059ed556271ccd4a25c88df066","last_reissued_at":"2026-07-05T10:05:16.966674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:16.966674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12554","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":"2026-07-05T10:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7212ykzP4padbYa3R0yf1AqPIXtSenDynNQEKExjVL633AVl7t4YJeZdeTClHbGCAd9xW4SYj/nIDOuPWr8PBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:01:08.351309Z"},"content_sha256":"92a77df59c13f56f425ff8f5500023a932d8fe287844eb8925fe03a9ee5f1c15","schema_version":"1.0","event_id":"sha256:92a77df59c13f56f425ff8f5500023a932d8fe287844eb8925fe03a9ee5f1c15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:47T7FI4QI2H56TLPPO7J3QWEKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization Performance of Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gonzalo R. Arce, Guangmo Tong, Yifan Wang","submitted_at":"2025-01-22T00:20:26Z","abstract_excerpt":"Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their generalization abilities in theory are less clear to us. In this paper, we seek to develop margin-based generalization bounds for four representative classes of hypergraph neural networks, including convolutional-based methods (UniGCN), set-based aggregation (AllDeepSets), invariant and equivariant transformations (M-IGN), and tensor-based approaches (T-MPH"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12554","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/2501.12554/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":"2026-07-05T10:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jilVxlD+hf5SICbch78ZAZpoofHIBOgD0XZWJjwZZv2fIOOgXwTWyOcijXb1f/X+uaUOsB16qt242mLQDWLoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:01:08.352270Z"},"content_sha256":"6260a96378910edb0c4d7959c97515706067bdc52b30cbd060da8b8475171a8a","schema_version":"1.0","event_id":"sha256:6260a96378910edb0c4d7959c97515706067bdc52b30cbd060da8b8475171a8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47T7FI4QI2H56TLPPO7J3QWEKG/bundle.json","state_url":"https://pith.science/pith/47T7FI4QI2H56TLPPO7J3QWEKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47T7FI4QI2H56TLPPO7J3QWEKG/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":"2026-08-11T07:01:08Z","links":{"resolver":"https://pith.science/pith/47T7FI4QI2H56TLPPO7J3QWEKG","bundle":"https://pith.science/pith/47T7FI4QI2H56TLPPO7J3QWEKG/bundle.json","state":"https://pith.science/pith/47T7FI4QI2H56TLPPO7J3QWEKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47T7FI4QI2H56TLPPO7J3QWEKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:47T7FI4QI2H56TLPPO7J3QWEKG","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":"d1281a55e71b4380ed9229ff46f608071119e51c07c7cde8c8eed3bb3e28ef6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T00:20:26Z","title_canon_sha256":"5a0949eef4a6c2d6fb3f4871506e22452f3642c2ae6593d0e4fd6bc9d55346d3"},"schema_version":"1.0","source":{"id":"2501.12554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12554","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12554v2","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12554","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"47T7FI4QI2H5","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"47T7FI4QI2H56TLP","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"47T7FI4Q","created_at":"2026-07-05T10:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:6260a96378910edb0c4d7959c97515706067bdc52b30cbd060da8b8475171a8a","target":"graph","created_at":"2026-07-05T10:05:16Z","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/2501.12554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their generalization abilities in theory are less clear to us. In this paper, we seek to develop margin-based generalization bounds for four representative classes of hypergraph neural networks, including convolutional-based methods (UniGCN), set-based aggregation (AllDeepSets), invariant and equivariant transformations (M-IGN), and tensor-based approaches (T-MPH","authors_text":"Gonzalo R. Arce, Guangmo Tong, Yifan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T00:20:26Z","title":"Generalization Performance of Hypergraph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12554","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":"sha256:92a77df59c13f56f425ff8f5500023a932d8fe287844eb8925fe03a9ee5f1c15","target":"record","created_at":"2026-07-05T10:05:16Z","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":"d1281a55e71b4380ed9229ff46f608071119e51c07c7cde8c8eed3bb3e28ef6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T00:20:26Z","title_canon_sha256":"5a0949eef4a6c2d6fb3f4871506e22452f3642c2ae6593d0e4fd6bc9d55346d3"},"schema_version":"1.0","source":{"id":"2501.12554","kind":"arxiv","version":2}},"canonical_sha256":"e7e7f2a390468fdf4d6f7bbe9dc2c4518708b5059ed556271ccd4a25c88df066","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7e7f2a390468fdf4d6f7bbe9dc2c4518708b5059ed556271ccd4a25c88df066","first_computed_at":"2026-07-05T10:05:16.966674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:16.966674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kXoTCZTGnBhDY8VNY43EwfQZW+Rn09JmwmndUKtY/XMIc06uhiBpMyKgQYVdTyMH6BuwunQnZLOC+HjDBIruCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:16.967139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92a77df59c13f56f425ff8f5500023a932d8fe287844eb8925fe03a9ee5f1c15","sha256:6260a96378910edb0c4d7959c97515706067bdc52b30cbd060da8b8475171a8a"],"state_sha256":"53d08aacb491d663f5c43ff9339883d3ec940924573c21b8d49c999336e81144"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9MOWLO+N44ORbExB9oScDxmEtcCoRGtHTdR+Yy2CLFLSOOatvikd9deG/ZFGURLtZHywFD0Ov7W7E5hgknlMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:01:08.360571Z","bundle_sha256":"53eeaf22653c269fb6bbff27f3e502975040c7c2874933ad007c597057acb632"}}