{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3XMUEARFUTPK5JHI4WKU4A6NVO","short_pith_number":"pith:3XMUEARF","canonical_record":{"source":{"id":"2501.14964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"a6aa6b4e88e3d0007ae1a98e78dc4ca63460aafa7f272bf8606e064851c2969c","abstract_canon_sha256":"9c9411f96acd0c80cef2579c9fc689e3662a770f497641d05ca87c1b5807fd66"},"schema_version":"1.0"},"canonical_sha256":"ddd9420225a4deaea4e8e5954e03cdabbde32a9569a1f5d4932953f26312c542","source":{"kind":"arxiv","id":"2501.14964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14964","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14964v2","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14964","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"3XMUEARFUTPK","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"3XMUEARFUTPK5JHI","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"3XMUEARF","created_at":"2026-07-05T11:23:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3XMUEARFUTPK5JHI4WKU4A6NVO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"a6aa6b4e88e3d0007ae1a98e78dc4ca63460aafa7f272bf8606e064851c2969c","abstract_canon_sha256":"9c9411f96acd0c80cef2579c9fc689e3662a770f497641d05ca87c1b5807fd66"},"schema_version":"1.0"},"canonical_sha256":"ddd9420225a4deaea4e8e5954e03cdabbde32a9569a1f5d4932953f26312c542","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:22.562103Z","signature_b64":"ham/57Vqrad4orM1jL0Mw7kNAcJ2b5wKELLCcwDYIXr0SutzbzEydjpMr3BThNmCoqCdQc5c8QUzvnmlr2WBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddd9420225a4deaea4e8e5954e03cdabbde32a9569a1f5d4932953f26312c542","last_reissued_at":"2026-07-05T11:23:22.561555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:22.561555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14964","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":"2026-07-05T11:23:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXLD5iDoNHku/Fy5iSo+6aswRUm8c4rcLQK+bR0KTfMpDFa1XZeI+2rj3uepKCD2SpbL3824jplQepsAZCF+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:19:07.905987Z"},"content_sha256":"cb39f90081fda09beb50e8fc88121cc52842aaac0077aa14d087883601967bef","schema_version":"1.0","event_id":"sha256:cb39f90081fda09beb50e8fc88121cc52842aaac0077aa14d087883601967bef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3XMUEARFUTPK5JHI4WKU4A6NVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalized Layer Selection for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kartik Sharma, Mahashweta Das, Srijan Kumar, Vineeth Rakesh, Yingtong Dou","submitted_at":"2025-01-24T22:49:53Z","abstract_excerpt":"Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect1, to se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14964","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/2501.14964/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":"2026-07-05T11:23:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0VNhSGQmEz6nkTjt6Dpq9jfUKTqng4A0ZBYTb4aCAoQNvLiXsjJ+ndUYTDxU++F+3DP9lDnqxwJUssVdlK8dAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:19:07.906606Z"},"content_sha256":"e40c568d9dcf8deab84dcce34c328bbdf63167ce4a2df6b8a5991f27846a8c05","schema_version":"1.0","event_id":"sha256:e40c568d9dcf8deab84dcce34c328bbdf63167ce4a2df6b8a5991f27846a8c05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/bundle.json","state_url":"https://pith.science/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/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":"2026-08-15T22:19:07Z","links":{"resolver":"https://pith.science/pith/3XMUEARFUTPK5JHI4WKU4A6NVO","bundle":"https://pith.science/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/bundle.json","state":"https://pith.science/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XMUEARFUTPK5JHI4WKU4A6NVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3XMUEARFUTPK5JHI4WKU4A6NVO","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":"9c9411f96acd0c80cef2579c9fc689e3662a770f497641d05ca87c1b5807fd66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:49:53Z","title_canon_sha256":"a6aa6b4e88e3d0007ae1a98e78dc4ca63460aafa7f272bf8606e064851c2969c"},"schema_version":"1.0","source":{"id":"2501.14964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14964","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14964v2","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14964","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"3XMUEARFUTPK","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"3XMUEARFUTPK5JHI","created_at":"2026-07-05T11:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"3XMUEARF","created_at":"2026-07-05T11:23:22Z"}],"graph_snapshots":[{"event_id":"sha256:e40c568d9dcf8deab84dcce34c328bbdf63167ce4a2df6b8a5991f27846a8c05","target":"graph","created_at":"2026-07-05T11:23:22Z","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/2501.14964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect1, to se","authors_text":"Kartik Sharma, Mahashweta Das, Srijan Kumar, Vineeth Rakesh, Yingtong Dou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:49:53Z","title":"Personalized Layer Selection for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14964","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:cb39f90081fda09beb50e8fc88121cc52842aaac0077aa14d087883601967bef","target":"record","created_at":"2026-07-05T11:23:22Z","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":"9c9411f96acd0c80cef2579c9fc689e3662a770f497641d05ca87c1b5807fd66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:49:53Z","title_canon_sha256":"a6aa6b4e88e3d0007ae1a98e78dc4ca63460aafa7f272bf8606e064851c2969c"},"schema_version":"1.0","source":{"id":"2501.14964","kind":"arxiv","version":2}},"canonical_sha256":"ddd9420225a4deaea4e8e5954e03cdabbde32a9569a1f5d4932953f26312c542","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddd9420225a4deaea4e8e5954e03cdabbde32a9569a1f5d4932953f26312c542","first_computed_at":"2026-07-05T11:23:22.561555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:22.561555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ham/57Vqrad4orM1jL0Mw7kNAcJ2b5wKELLCcwDYIXr0SutzbzEydjpMr3BThNmCoqCdQc5c8QUzvnmlr2WBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:22.562103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb39f90081fda09beb50e8fc88121cc52842aaac0077aa14d087883601967bef","sha256:e40c568d9dcf8deab84dcce34c328bbdf63167ce4a2df6b8a5991f27846a8c05"],"state_sha256":"aa87b7b5f511fb52454643a5fa8834db0d2c92dadd5750a5f18d312673bdbc57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbYjqI68TpN38iTp8q9IAAEtGJXnnP4ldNAuY68B9HPDsbrfLE2fHfe2i/Wym1qEnC+0WwqC/vXKatZrDlPVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:19:07.913230Z","bundle_sha256":"2713aff86f9b02bf34220bd3bb86be504ac4f1873c7c8a8c59660bbcd5638178"}}