{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MOGYXZSKGXFE2QKMYSDRIGR46F","short_pith_number":"pith:MOGYXZSK","canonical_record":{"source":{"id":"2504.13034","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T15:42:13Z","cross_cats_sorted":[],"title_canon_sha256":"32c86de95d22f3b7689c446f7928ce8f003a68a81210f285b039a11b6786e0ec","abstract_canon_sha256":"b86a7743ce9573297143d399eafeb3bce712c48aafdd19bec7985bc884835178"},"schema_version":"1.0"},"canonical_sha256":"638d8be64a35ca4d414cc487141a3cf143a069d0ef5653cfce278d8c69649dfc","source":{"kind":"arxiv","id":"2504.13034","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13034","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13034v3","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13034","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_12","alias_value":"MOGYXZSKGXFE","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_16","alias_value":"MOGYXZSKGXFE2QKM","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_8","alias_value":"MOGYXZSK","created_at":"2026-07-05T11:01:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MOGYXZSKGXFE2QKMYSDRIGR46F","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13034","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T15:42:13Z","cross_cats_sorted":[],"title_canon_sha256":"32c86de95d22f3b7689c446f7928ce8f003a68a81210f285b039a11b6786e0ec","abstract_canon_sha256":"b86a7743ce9573297143d399eafeb3bce712c48aafdd19bec7985bc884835178"},"schema_version":"1.0"},"canonical_sha256":"638d8be64a35ca4d414cc487141a3cf143a069d0ef5653cfce278d8c69649dfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:04.277048Z","signature_b64":"uV3jzV6wPjXpDoPi66rODFhA2O1thQFIR/JtKfzlQTcM6Jvjgeu7NXpFgsVpXrUQkUMu5uMvDJ4Xm5TB/dt7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638d8be64a35ca4d414cc487141a3cf143a069d0ef5653cfce278d8c69649dfc","last_reissued_at":"2026-07-05T11:01:04.276545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:04.276545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13034","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HybmKtMV5IQyVSiQMjDM7SZvaA7ahEjkU+BPn6YI5NSTRW/YsHN3udUeOhLX7Sre7YkZKvQWj3Z/UdI2ViG7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:10:56.140231Z"},"content_sha256":"50f51adf10093aa811d3bef001b031840ac2bb26320f3be89404ccc28e37ce5b","schema_version":"1.0","event_id":"sha256:50f51adf10093aa811d3bef001b031840ac2bb26320f3be89404ccc28e37ce5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MOGYXZSKGXFE2QKMYSDRIGR46F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference-friendly Graph Compression for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haolai Che, Yangxin Fan, Yinghui Wu","submitted_at":"2025-04-17T15:42:13Z","abstract_excerpt":"Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph $G$ and a GNN $M$, an IFGC computes a small compressed graph $G_c$, to best preserve the inference results of $M$ over $G$, such that the result can be directly inferred by accessing $G_c$ with no or little decompression cost. (1) We characterize IFGC with a class of i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13034","kind":"arxiv","version":3},"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/2504.13034/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":"2026-07-05T11:01:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZIJCqFEswZbQFAKvdnvKICCvqOxe++XN3+F1CBegn5lAnospKTx0W5GIoysvUGtAAF+gdpeZyrdSYjd0NzmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:10:56.140752Z"},"content_sha256":"7f1649e1fc6108484b0550f27182e8372f3bcbe6583ab98781fdca98145a2d0c","schema_version":"1.0","event_id":"sha256:7f1649e1fc6108484b0550f27182e8372f3bcbe6583ab98781fdca98145a2d0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/bundle.json","state_url":"https://pith.science/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/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":"2026-08-19T20:10:56Z","links":{"resolver":"https://pith.science/pith/MOGYXZSKGXFE2QKMYSDRIGR46F","bundle":"https://pith.science/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/bundle.json","state":"https://pith.science/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOGYXZSKGXFE2QKMYSDRIGR46F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MOGYXZSKGXFE2QKMYSDRIGR46F","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":"b86a7743ce9573297143d399eafeb3bce712c48aafdd19bec7985bc884835178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T15:42:13Z","title_canon_sha256":"32c86de95d22f3b7689c446f7928ce8f003a68a81210f285b039a11b6786e0ec"},"schema_version":"1.0","source":{"id":"2504.13034","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13034","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13034v3","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13034","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_12","alias_value":"MOGYXZSKGXFE","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_16","alias_value":"MOGYXZSKGXFE2QKM","created_at":"2026-07-05T11:01:04Z"},{"alias_kind":"pith_short_8","alias_value":"MOGYXZSK","created_at":"2026-07-05T11:01:04Z"}],"graph_snapshots":[{"event_id":"sha256:7f1649e1fc6108484b0550f27182e8372f3bcbe6583ab98781fdca98145a2d0c","target":"graph","created_at":"2026-07-05T11:01:04Z","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/2504.13034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph $G$ and a GNN $M$, an IFGC computes a small compressed graph $G_c$, to best preserve the inference results of $M$ over $G$, such that the result can be directly inferred by accessing $G_c$ with no or little decompression cost. (1) We characterize IFGC with a class of i","authors_text":"Haolai Che, Yangxin Fan, Yinghui Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T15:42:13Z","title":"Inference-friendly Graph Compression for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13034","kind":"arxiv","version":3},"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":"sha256:50f51adf10093aa811d3bef001b031840ac2bb26320f3be89404ccc28e37ce5b","target":"record","created_at":"2026-07-05T11:01:04Z","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":"b86a7743ce9573297143d399eafeb3bce712c48aafdd19bec7985bc884835178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T15:42:13Z","title_canon_sha256":"32c86de95d22f3b7689c446f7928ce8f003a68a81210f285b039a11b6786e0ec"},"schema_version":"1.0","source":{"id":"2504.13034","kind":"arxiv","version":3}},"canonical_sha256":"638d8be64a35ca4d414cc487141a3cf143a069d0ef5653cfce278d8c69649dfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"638d8be64a35ca4d414cc487141a3cf143a069d0ef5653cfce278d8c69649dfc","first_computed_at":"2026-07-05T11:01:04.276545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:04.276545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uV3jzV6wPjXpDoPi66rODFhA2O1thQFIR/JtKfzlQTcM6Jvjgeu7NXpFgsVpXrUQkUMu5uMvDJ4Xm5TB/dt7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:04.277048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13034","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50f51adf10093aa811d3bef001b031840ac2bb26320f3be89404ccc28e37ce5b","sha256:7f1649e1fc6108484b0550f27182e8372f3bcbe6583ab98781fdca98145a2d0c"],"state_sha256":"ea359b25d5ee6b3a327bb3f135a1d4b84e816b61376770174f124a9f6466adb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3d5QxcDkgqYOyksRl4pEuuhqxfBRXTnSc5aIU+rYc3AE8Vg/z1wVhPGbIH2jANWUcebeK5xvj1nb/AnREwDkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:10:56.145893Z","bundle_sha256":"1610db4bd2440f0eafa217ef6ad33aba87fef8d7c5dcc8333245e901f644d18e"}}