{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KDNY7HLLGCUCA64S4YE2KEWMW2","short_pith_number":"pith:KDNY7HLL","canonical_record":{"source":{"id":"2106.05609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"a5855e840834025c8e8645824b2f65883c37d8dabd5fd2229f854cc965ac5ccc","abstract_canon_sha256":"77d809c07757762d78912aff34f03d7e291f1fa90639d8b5679cd65ec27551c1"},"schema_version":"1.0"},"canonical_sha256":"50db8f9d6b30a8207b92e609a512ccb6a1040e029edcd913cd7c39c1d4a8ff1c","source":{"kind":"arxiv","id":"2106.05609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05609","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05609v1","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05609","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"KDNY7HLLGCUC","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"KDNY7HLLGCUCA64S","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"KDNY7HLL","created_at":"2026-07-05T02:48:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KDNY7HLLGCUCA64S4YE2KEWMW2","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"a5855e840834025c8e8645824b2f65883c37d8dabd5fd2229f854cc965ac5ccc","abstract_canon_sha256":"77d809c07757762d78912aff34f03d7e291f1fa90639d8b5679cd65ec27551c1"},"schema_version":"1.0"},"canonical_sha256":"50db8f9d6b30a8207b92e609a512ccb6a1040e029edcd913cd7c39c1d4a8ff1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:03.467340Z","signature_b64":"BVhBZJrh9f+mV/CFdaB9ny67j+0FZgKois58OTfdZxGnVeIU7eAasrbbmlpqoqX2cVfR6knVrHKUTQP1LuSyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50db8f9d6b30a8207b92e609a512ccb6a1040e029edcd913cd7c39c1d4a8ff1c","last_reissued_at":"2026-07-05T02:48:03.466901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:03.466901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05609","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":"2026-07-05T02:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uu5uIWQCzp0hjF36FEbwze+fcV/WBjASAodee6nXmjoXoIuqL57+KInA2QBmnKb3WTmlBr8MFyt6cpwWJxkgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:45:24.035687Z"},"content_sha256":"0472b092f50c7688f4e47ed41fd34cb88ba575227aa92dfffb8e2008e54277ed","schema_version":"1.0","event_id":"sha256:0472b092f50c7688f4e47ed41fd34cb88ba575227aa92dfffb8e2008e54277ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KDNY7HLLGCUCA64S4YE2KEWMW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Weichert, Jan E. Lenssen, Jure Leskovec, Matthias Fey","submitted_at":"2021-06-10T09:26:56Z","abstract_excerpt":"We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size without dropping any data. While existing solutions weaken the expressive power of message passing due to sub-sampling of edges or non-trainable propagations, our approach is provably able to maintain the expressive power of the original GNN. We achieve this by providing approximation error bounds of hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05609","kind":"arxiv","version":1},"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/2106.05609/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":"2026-07-05T02:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEaz0WWCVJ8aU3c5I6r7B9BsmwlbnXODDS1iRtDhE4Y40LI38ihc+hY4wXZMP1fUC5n5ANy4AyDBdxBwxmAtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:45:24.036210Z"},"content_sha256":"db93b78e1882958942179133cf318f395b816d1d912402774171bb82a502dbd9","schema_version":"1.0","event_id":"sha256:db93b78e1882958942179133cf318f395b816d1d912402774171bb82a502dbd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/bundle.json","state_url":"https://pith.science/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/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":"2026-08-06T17:45:24Z","links":{"resolver":"https://pith.science/pith/KDNY7HLLGCUCA64S4YE2KEWMW2","bundle":"https://pith.science/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/bundle.json","state":"https://pith.science/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDNY7HLLGCUCA64S4YE2KEWMW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KDNY7HLLGCUCA64S4YE2KEWMW2","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":"77d809c07757762d78912aff34f03d7e291f1fa90639d8b5679cd65ec27551c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:26:56Z","title_canon_sha256":"a5855e840834025c8e8645824b2f65883c37d8dabd5fd2229f854cc965ac5ccc"},"schema_version":"1.0","source":{"id":"2106.05609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05609","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05609v1","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05609","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"KDNY7HLLGCUC","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"KDNY7HLLGCUCA64S","created_at":"2026-07-05T02:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"KDNY7HLL","created_at":"2026-07-05T02:48:03Z"}],"graph_snapshots":[{"event_id":"sha256:db93b78e1882958942179133cf318f395b816d1d912402774171bb82a502dbd9","target":"graph","created_at":"2026-07-05T02:48:03Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.05609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size without dropping any data. While existing solutions weaken the expressive power of message passing due to sub-sampling of edges or non-trainable propagations, our approach is provably able to maintain the expressive power of the original GNN. We achieve this by providing approximation error bounds of hi","authors_text":"Frank Weichert, Jan E. Lenssen, Jure Leskovec, Matthias Fey","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:26:56Z","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05609","kind":"arxiv","version":1},"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":"sha256:0472b092f50c7688f4e47ed41fd34cb88ba575227aa92dfffb8e2008e54277ed","target":"record","created_at":"2026-07-05T02:48:03Z","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":"77d809c07757762d78912aff34f03d7e291f1fa90639d8b5679cd65ec27551c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:26:56Z","title_canon_sha256":"a5855e840834025c8e8645824b2f65883c37d8dabd5fd2229f854cc965ac5ccc"},"schema_version":"1.0","source":{"id":"2106.05609","kind":"arxiv","version":1}},"canonical_sha256":"50db8f9d6b30a8207b92e609a512ccb6a1040e029edcd913cd7c39c1d4a8ff1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50db8f9d6b30a8207b92e609a512ccb6a1040e029edcd913cd7c39c1d4a8ff1c","first_computed_at":"2026-07-05T02:48:03.466901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:03.466901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BVhBZJrh9f+mV/CFdaB9ny67j+0FZgKois58OTfdZxGnVeIU7eAasrbbmlpqoqX2cVfR6knVrHKUTQP1LuSyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:03.467340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0472b092f50c7688f4e47ed41fd34cb88ba575227aa92dfffb8e2008e54277ed","sha256:db93b78e1882958942179133cf318f395b816d1d912402774171bb82a502dbd9"],"state_sha256":"328461323a0adb4c6b9e49282e0e40246a84acfb864f7f132b4a12ee9dbeec89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1MAzAaP+zJ6ZUzZ53eBwHwc7QuaJtapcFbTLwf7E9UA9V+WDrM/YZT+k24VN4cAq3MkrQTC4s+4QTT1omsaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:45:24.042569Z","bundle_sha256":"e2e05bee07e4c06df425d2d90ceffd2e77e6c429fd42fb67a98888af7c5c483c"}}