{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PZTKKXXUNCUB3SNSPNQJUYYCVV","short_pith_number":"pith:PZTKKXXU","canonical_record":{"source":{"id":"2506.14098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T01:28:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f761a7da8fe8dd1a7ade22822253f4223717cb75bfa35dfedcb55725b8703b1","abstract_canon_sha256":"10c5a6c75718f8d8a37b13ed3cb13ff6b2cf9982e55a104e0ef727e3bafb52db"},"schema_version":"1.0"},"canonical_sha256":"7e66a55ef468a81dc9b27b609a6302ad7a9bdc5ebe7e42194ef12fb370597994","source":{"kind":"arxiv","id":"2506.14098","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14098","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14098v1","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14098","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"PZTKKXXUNCUB","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"PZTKKXXUNCUB3SNS","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"PZTKKXXU","created_at":"2026-07-05T11:22:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PZTKKXXUNCUB3SNSPNQJUYYCVV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T01:28:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f761a7da8fe8dd1a7ade22822253f4223717cb75bfa35dfedcb55725b8703b1","abstract_canon_sha256":"10c5a6c75718f8d8a37b13ed3cb13ff6b2cf9982e55a104e0ef727e3bafb52db"},"schema_version":"1.0"},"canonical_sha256":"7e66a55ef468a81dc9b27b609a6302ad7a9bdc5ebe7e42194ef12fb370597994","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:48.963862Z","signature_b64":"/aHHjnGv5m0Ud0VVsfZb2HCXXFRFU6fxrlMGj6PbJD5uCYTNcAKoJhgm/LoFpPY0abDzLTkH5xsQF8OYOU9IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e66a55ef468a81dc9b27b609a6302ad7a9bdc5ebe7e42194ef12fb370597994","last_reissued_at":"2026-07-05T11:22:48.963359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:48.963359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14098","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":"2026-07-05T11:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRgqfhfFDOOdNv8KR3R4hx8KrAIdMUT9qO59mw8zDkoW7sJP+pV+0RREPIkcEY0UlIaHEghufDYQEQUYyLM/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:28:05.266265Z"},"content_sha256":"79c944b37f118f71b256e54a829b8ac286496786a14b7e44d01ffcfeaf0a5151","schema_version":"1.0","event_id":"sha256:79c944b37f118f71b256e54a829b8ac286496786a14b7e44d01ffcfeaf0a5151"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PZTKKXXUNCUB3SNSPNQJUYYCVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Chen, Ziyuan Tang","submitted_at":"2025-06-17T01:28:34Z","abstract_excerpt":"A foundation model like GPT elicits many emergent abilities, owing to the pre-training with broad inclusion of data and the use of the powerful Transformer architecture. While foundation models in natural languages are prevalent, can we build similar models for graphs? This paper describes an approach toward a graph foundation model that is pre-trained with diverse graph datasets by adapting the Transformer backbone. A central challenge toward this end is how a sequence model encodes graphs of varying sizes and from different domains. We propose representing a node as multiple random walks, su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14098","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/2506.14098/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":"2026-07-05T11:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YLoPgHR3uo4HO287hXvGMhq5cP8E4uQjU8GVEWcrjhhMNy0/32jkUEPkxeknm6oU4ngAcoiSsTs2FVuFhgbqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:28:05.266822Z"},"content_sha256":"d0e6e89f03b8263f713c9b637d95730d2ae3307f187ae6428ddb55506222062d","schema_version":"1.0","event_id":"sha256:d0e6e89f03b8263f713c9b637d95730d2ae3307f187ae6428ddb55506222062d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/bundle.json","state_url":"https://pith.science/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/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":"2026-08-16T20:28:05Z","links":{"resolver":"https://pith.science/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV","bundle":"https://pith.science/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/bundle.json","state":"https://pith.science/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZTKKXXUNCUB3SNSPNQJUYYCVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PZTKKXXUNCUB3SNSPNQJUYYCVV","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":"10c5a6c75718f8d8a37b13ed3cb13ff6b2cf9982e55a104e0ef727e3bafb52db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T01:28:34Z","title_canon_sha256":"9f761a7da8fe8dd1a7ade22822253f4223717cb75bfa35dfedcb55725b8703b1"},"schema_version":"1.0","source":{"id":"2506.14098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14098","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14098v1","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14098","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"PZTKKXXUNCUB","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"PZTKKXXUNCUB3SNS","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"PZTKKXXU","created_at":"2026-07-05T11:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:d0e6e89f03b8263f713c9b637d95730d2ae3307f187ae6428ddb55506222062d","target":"graph","created_at":"2026-07-05T11:22:48Z","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/2506.14098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A foundation model like GPT elicits many emergent abilities, owing to the pre-training with broad inclusion of data and the use of the powerful Transformer architecture. While foundation models in natural languages are prevalent, can we build similar models for graphs? This paper describes an approach toward a graph foundation model that is pre-trained with diverse graph datasets by adapting the Transformer backbone. A central challenge toward this end is how a sequence model encodes graphs of varying sizes and from different domains. We propose representing a node as multiple random walks, su","authors_text":"Jie Chen, Ziyuan Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14098","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":"sha256:79c944b37f118f71b256e54a829b8ac286496786a14b7e44d01ffcfeaf0a5151","target":"record","created_at":"2026-07-05T11:22:48Z","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":"10c5a6c75718f8d8a37b13ed3cb13ff6b2cf9982e55a104e0ef727e3bafb52db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T01:28:34Z","title_canon_sha256":"9f761a7da8fe8dd1a7ade22822253f4223717cb75bfa35dfedcb55725b8703b1"},"schema_version":"1.0","source":{"id":"2506.14098","kind":"arxiv","version":1}},"canonical_sha256":"7e66a55ef468a81dc9b27b609a6302ad7a9bdc5ebe7e42194ef12fb370597994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e66a55ef468a81dc9b27b609a6302ad7a9bdc5ebe7e42194ef12fb370597994","first_computed_at":"2026-07-05T11:22:48.963359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:48.963359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/aHHjnGv5m0Ud0VVsfZb2HCXXFRFU6fxrlMGj6PbJD5uCYTNcAKoJhgm/LoFpPY0abDzLTkH5xsQF8OYOU9IBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:48.963862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79c944b37f118f71b256e54a829b8ac286496786a14b7e44d01ffcfeaf0a5151","sha256:d0e6e89f03b8263f713c9b637d95730d2ae3307f187ae6428ddb55506222062d"],"state_sha256":"e84899ca8f27a5b5c3a25b0865b31291f463b473a7f129a8d865a28fb8608bf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EoPyvjHsGhYc1OD3nahlZRhn/kgi9FMYrB5NDbiBT5SNsCb1xeiYzprCDSqLz1goXxl3Lw3LUZUrIUqJqKpTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:28:05.270418Z","bundle_sha256":"d534d8703dd4ed93b867a491bfd7d2140197177d4d6c871fad0594101e3ee915"}}