{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IGMKXJEOWWMQCNZ3B3XQNHHXL5","short_pith_number":"pith:IGMKXJEO","canonical_record":{"source":{"id":"2409.05477","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T10:11:25Z","cross_cats_sorted":[],"title_canon_sha256":"34c4060ac525010caa87537b8b5261971012975ba6f1c2652a8a1c857b2b125e","abstract_canon_sha256":"39350e7a75e785927011807760a56819b47793a0767673f633e4ee1581c8639e"},"schema_version":"1.0"},"canonical_sha256":"4198aba48eb59901373b0eef069cf75f7207ae196f550d46e79576ee0ba6426f","source":{"kind":"arxiv","id":"2409.05477","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05477","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05477v3","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05477","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"IGMKXJEOWWMQ","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"IGMKXJEOWWMQCNZ3","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"IGMKXJEO","created_at":"2026-07-05T09:08:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IGMKXJEOWWMQCNZ3B3XQNHHXL5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.05477","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T10:11:25Z","cross_cats_sorted":[],"title_canon_sha256":"34c4060ac525010caa87537b8b5261971012975ba6f1c2652a8a1c857b2b125e","abstract_canon_sha256":"39350e7a75e785927011807760a56819b47793a0767673f633e4ee1581c8639e"},"schema_version":"1.0"},"canonical_sha256":"4198aba48eb59901373b0eef069cf75f7207ae196f550d46e79576ee0ba6426f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:29.222999Z","signature_b64":"B5GIh4a2s9hsJF9DQr/95mG/pw5QCDeRrOwiq3Hx3TtnqdZGbpYzrhBvqGQl4632nemXp/AffsikX/FCyDElDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4198aba48eb59901373b0eef069cf75f7207ae196f550d46e79576ee0ba6426f","last_reissued_at":"2026-07-05T09:08:29.222502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:29.222502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.05477","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":"2026-07-05T09:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbhMfxdS6cHiOsVoZuIJxa9la7MukFPcGMOVrWLG2weVjbzk5aZgmdPWVGhXiOxYM4yC5zugaEi3aOl0juZLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:26:35.821260Z"},"content_sha256":"7ddd3530c81940ad4690901c49ab4108d3850d8fe90463b18ff945ae105262af","schema_version":"1.0","event_id":"sha256:7ddd3530c81940ad4690901c49ab4108d3850d8fe90463b18ff945ae105262af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IGMKXJEOWWMQCNZ3B3XQNHHXL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrofitting Temporal Graph Neural Networks with Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangcheng Fu, Jiawei Jiang, Qiang Huang, Susie Xi Rao, Wentao Zhang, Xiao Yan, Xin Wang, Zhichao Han","submitted_at":"2024-09-09T10:11:25Z","abstract_excerpt":"Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks (e.g., TGL and ETC). In this paper, we propose TF-TGN, which uses Transformer decoder as the backbone model for TGNN to enjoy Transformer's codebase for efficient training. In particular, Transformer achieves tremendous success for language modeling, and thus the community developed high-performance kernels (e.g., flash-attention and memory-efficient attention) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05477","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/2409.05477/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":"2026-07-05T09:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vz2BxcSF4BRX3j/DaN4RPN9gQh2QnkrJ8yow/aMTQj4UODse7sItCrf4esqxzLPCI2zpssP+8aNMJgsMs3dCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:26:35.821788Z"},"content_sha256":"1f798d4e865ae873d65c429bd3b57232a9664af3b823d54ad905745843d75cd1","schema_version":"1.0","event_id":"sha256:1f798d4e865ae873d65c429bd3b57232a9664af3b823d54ad905745843d75cd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/bundle.json","state_url":"https://pith.science/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/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":"2026-08-14T17:26:35Z","links":{"resolver":"https://pith.science/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5","bundle":"https://pith.science/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/bundle.json","state":"https://pith.science/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGMKXJEOWWMQCNZ3B3XQNHHXL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IGMKXJEOWWMQCNZ3B3XQNHHXL5","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":"39350e7a75e785927011807760a56819b47793a0767673f633e4ee1581c8639e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T10:11:25Z","title_canon_sha256":"34c4060ac525010caa87537b8b5261971012975ba6f1c2652a8a1c857b2b125e"},"schema_version":"1.0","source":{"id":"2409.05477","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05477","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05477v3","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05477","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"IGMKXJEOWWMQ","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"IGMKXJEOWWMQCNZ3","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"IGMKXJEO","created_at":"2026-07-05T09:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:1f798d4e865ae873d65c429bd3b57232a9664af3b823d54ad905745843d75cd1","target":"graph","created_at":"2026-07-05T09:08:29Z","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/2409.05477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks (e.g., TGL and ETC). In this paper, we propose TF-TGN, which uses Transformer decoder as the backbone model for TGNN to enjoy Transformer's codebase for efficient training. In particular, Transformer achieves tremendous success for language modeling, and thus the community developed high-performance kernels (e.g., flash-attention and memory-efficient attention) ","authors_text":"Fangcheng Fu, Jiawei Jiang, Qiang Huang, Susie Xi Rao, Wentao Zhang, Xiao Yan, Xin Wang, Zhichao Han","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T10:11:25Z","title":"Retrofitting Temporal Graph Neural Networks with Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05477","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":"sha256:7ddd3530c81940ad4690901c49ab4108d3850d8fe90463b18ff945ae105262af","target":"record","created_at":"2026-07-05T09:08:29Z","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":"39350e7a75e785927011807760a56819b47793a0767673f633e4ee1581c8639e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T10:11:25Z","title_canon_sha256":"34c4060ac525010caa87537b8b5261971012975ba6f1c2652a8a1c857b2b125e"},"schema_version":"1.0","source":{"id":"2409.05477","kind":"arxiv","version":3}},"canonical_sha256":"4198aba48eb59901373b0eef069cf75f7207ae196f550d46e79576ee0ba6426f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4198aba48eb59901373b0eef069cf75f7207ae196f550d46e79576ee0ba6426f","first_computed_at":"2026-07-05T09:08:29.222502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:29.222502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B5GIh4a2s9hsJF9DQr/95mG/pw5QCDeRrOwiq3Hx3TtnqdZGbpYzrhBvqGQl4632nemXp/AffsikX/FCyDElDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:29.222999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05477","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ddd3530c81940ad4690901c49ab4108d3850d8fe90463b18ff945ae105262af","sha256:1f798d4e865ae873d65c429bd3b57232a9664af3b823d54ad905745843d75cd1"],"state_sha256":"080fcef378d9943221527d96d733bc53dd7b6c22287b770b9b8d6548b316c325"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHoEvTrnGA7K1+KvOx5vT7990NUSclqXIHli6VsiJFy3ihjwvzImshxOSsIk44yfjFOL4pUWVNrKMnmnJyuGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:26:35.835567Z","bundle_sha256":"8a129049961a5cfa5d21b4b92ff8ed61b63ce7df24b9404f141e047a32fcd457"}}