{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U4IN3O5J7UGHK6DDPQBTS36Y6G","short_pith_number":"pith:U4IN3O5J","canonical_record":{"source":{"id":"2501.08547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-15T03:14:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4785eb52e3638005da01637007a46181c98399397aee6e55d8d23edd9e9a57d2","abstract_canon_sha256":"fc49927a984722e83aeeefaf34b8407300d4c2d02c3467c69d870eee749ee3a6"},"schema_version":"1.0"},"canonical_sha256":"a710ddbba9fd0c7578637c03396fd8f1b1c468f635ce90db2e6d5a5a377bdee5","source":{"kind":"arxiv","id":"2501.08547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08547","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08547v1","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08547","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"U4IN3O5J7UGH","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"U4IN3O5J7UGHK6DD","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"U4IN3O5J","created_at":"2026-07-05T10:01:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U4IN3O5J7UGHK6DDPQBTS36Y6G","target":"record","payload":{"canonical_record":{"source":{"id":"2501.08547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-15T03:14:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4785eb52e3638005da01637007a46181c98399397aee6e55d8d23edd9e9a57d2","abstract_canon_sha256":"fc49927a984722e83aeeefaf34b8407300d4c2d02c3467c69d870eee749ee3a6"},"schema_version":"1.0"},"canonical_sha256":"a710ddbba9fd0c7578637c03396fd8f1b1c468f635ce90db2e6d5a5a377bdee5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:21.048363Z","signature_b64":"+K4Ri9zHTehSTfTUJXp/Wzs1RF/ankOydyq83VN4F9dneIZDQUtiDDkqUV9EPkLOah7/BxUeVWfx8t+29QoWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a710ddbba9fd0c7578637c03396fd8f1b1c468f635ce90db2e6d5a5a377bdee5","last_reissued_at":"2026-07-05T10:01:21.047933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:21.047933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.08547","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":"2026-07-05T10:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jRHndLQ457XQjX/vw8qCrN4OCDh3Fp7jvs0h+NyALiZ25yzod3ZupRCLa6HlSmhoujeDN95EG9jEfSfvkTICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:35:34.481037Z"},"content_sha256":"7da8aaf6e4ec106e514c1076fcfb02df2b181d29d8a55f2d5557dd3db5a9ffd1","schema_version":"1.0","event_id":"sha256:7da8aaf6e4ec106e514c1076fcfb02df2b181d29d8a55f2d5557dd3db5a9ffd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U4IN3O5J7UGHK6DDPQBTS36Y6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OMEGA: A Low-Latency GNN Serving System for Large Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Aditya Akella, Anand Iyer, Daehyeok Kim, Donghyun Kim, Geon-Woo Kim, Henry Liu, Jeongyoon Moon, Tarannum Khan","submitted_at":"2025-01-15T03:14:18Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose OMEGA, a system that enables low-latency GNN serving for large graphs with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08547","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/2501.08547/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":"2026-07-05T10:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mM8uQAcrFNpcx891L2cjkPFowD7FnxrNQBgCOsYVKYh+JIAZg33vzT0pwx6keLRj/RFy2UIM1rhFU4pHUnS0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:35:34.481591Z"},"content_sha256":"1931daffdbc49e25107187d7f91e708f5ff57225e63c026fdbb4b4abecedb3e7","schema_version":"1.0","event_id":"sha256:1931daffdbc49e25107187d7f91e708f5ff57225e63c026fdbb4b4abecedb3e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/bundle.json","state_url":"https://pith.science/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/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":"2026-08-20T00:35:34Z","links":{"resolver":"https://pith.science/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G","bundle":"https://pith.science/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/bundle.json","state":"https://pith.science/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4IN3O5J7UGHK6DDPQBTS36Y6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4IN3O5J7UGHK6DDPQBTS36Y6G","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":"fc49927a984722e83aeeefaf34b8407300d4c2d02c3467c69d870eee749ee3a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-15T03:14:18Z","title_canon_sha256":"4785eb52e3638005da01637007a46181c98399397aee6e55d8d23edd9e9a57d2"},"schema_version":"1.0","source":{"id":"2501.08547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08547","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08547v1","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08547","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"U4IN3O5J7UGH","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"U4IN3O5J7UGHK6DD","created_at":"2026-07-05T10:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"U4IN3O5J","created_at":"2026-07-05T10:01:21Z"}],"graph_snapshots":[{"event_id":"sha256:1931daffdbc49e25107187d7f91e708f5ff57225e63c026fdbb4b4abecedb3e7","target":"graph","created_at":"2026-07-05T10:01:21Z","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/2501.08547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose OMEGA, a system that enables low-latency GNN serving for large graphs with","authors_text":"Aditya Akella, Anand Iyer, Daehyeok Kim, Donghyun Kim, Geon-Woo Kim, Henry Liu, Jeongyoon Moon, Tarannum Khan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-15T03:14:18Z","title":"OMEGA: A Low-Latency GNN Serving System for Large Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08547","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":"sha256:7da8aaf6e4ec106e514c1076fcfb02df2b181d29d8a55f2d5557dd3db5a9ffd1","target":"record","created_at":"2026-07-05T10:01:21Z","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":"fc49927a984722e83aeeefaf34b8407300d4c2d02c3467c69d870eee749ee3a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-15T03:14:18Z","title_canon_sha256":"4785eb52e3638005da01637007a46181c98399397aee6e55d8d23edd9e9a57d2"},"schema_version":"1.0","source":{"id":"2501.08547","kind":"arxiv","version":1}},"canonical_sha256":"a710ddbba9fd0c7578637c03396fd8f1b1c468f635ce90db2e6d5a5a377bdee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a710ddbba9fd0c7578637c03396fd8f1b1c468f635ce90db2e6d5a5a377bdee5","first_computed_at":"2026-07-05T10:01:21.047933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:21.047933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+K4Ri9zHTehSTfTUJXp/Wzs1RF/ankOydyq83VN4F9dneIZDQUtiDDkqUV9EPkLOah7/BxUeVWfx8t+29QoWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:21.048363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7da8aaf6e4ec106e514c1076fcfb02df2b181d29d8a55f2d5557dd3db5a9ffd1","sha256:1931daffdbc49e25107187d7f91e708f5ff57225e63c026fdbb4b4abecedb3e7"],"state_sha256":"293de8cef97fbb15ba0387e63012d223119571cac825432fedc059e45f533e4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLAYB7+c5tQ9z+eSSnDGOftOKATDqD+GjjISG/t4oT8DZnt8lwmpluZvDCNGCGkw0tuvwbZ5ODYWW7HQkfNgDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T00:35:34.485716Z","bundle_sha256":"15deed3c70109b3e39233fce3aed928a5e35e20f4e03fcc840c1d2126805c2fe"}}