{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R3EDN5WG4PVBS33UAULFFZNSN7","short_pith_number":"pith:R3EDN5WG","canonical_record":{"source":{"id":"2606.05116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"9f358387fbb2e6f74c96bb08b4c1084022b0fb46dc36ab3235fefc8afef7a348","abstract_canon_sha256":"25bfc167a06dc2f918796a8b18c3a944045f2a4bbb7fddcc63c16fbec9c7b69f"},"schema_version":"1.0"},"canonical_sha256":"8ec836f6c6e3ea196f74051652e5b26ff8c2e64ddb0a3d181574efbaa9eec9a4","source":{"kind":"arxiv","id":"2606.05116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05116","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05116v1","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05116","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"R3EDN5WG4PVB","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"R3EDN5WG4PVBS33U","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"R3EDN5WG","created_at":"2026-06-04T01:10:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R3EDN5WG4PVBS33UAULFFZNSN7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"9f358387fbb2e6f74c96bb08b4c1084022b0fb46dc36ab3235fefc8afef7a348","abstract_canon_sha256":"25bfc167a06dc2f918796a8b18c3a944045f2a4bbb7fddcc63c16fbec9c7b69f"},"schema_version":"1.0"},"canonical_sha256":"8ec836f6c6e3ea196f74051652e5b26ff8c2e64ddb0a3d181574efbaa9eec9a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:06.913916Z","signature_b64":"ap8VFgEJODSp+TGgeWn+eQVQYaj6w6qqN6b6NOmG5t55tSGyu7nySCTZG1fh/AVhBbcIr66WeAjWgzDKqIUkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec836f6c6e3ea196f74051652e5b26ff8c2e64ddb0a3d181574efbaa9eec9a4","last_reissued_at":"2026-06-04T01:10:06.913282Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:06.913282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05116","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":"2026-06-04T01:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GxfXyzYk1ITmOZrKR+ZEGwAX3ZP0kuj307OyPtBDMIzqL/nbYf19Bhyr5LCOiy77NVrsx2VFqZ2YZsXUvwRrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:13:19.476098Z"},"content_sha256":"ec3855bb974449b25856453c95afebbd8e6eff69d314066eba81aa3b5e1b49c6","schema_version":"1.0","event_id":"sha256:ec3855bb974449b25856453c95afebbd8e6eff69d314066eba81aa3b5e1b49c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R3EDN5WG4PVBS33UAULFFZNSN7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Set Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baoquan Chen, Daniel Probst, Jose E. Escrig Molina","submitted_at":"2026-06-03T17:20:48Z","abstract_excerpt":"We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure. Existing architectures, including DeepSets and SetTransformer, require pre-encoded graph embeddings from a separate GNN, creating a bottleneck between feature extraction and set-level contextualisation. In contrast, GST interleaves node-level feature propagation and cross-graph contextual modelling at every layer, fusing the two levels of information through a gating mechanism. We e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05116","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/2606.05116/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":"2026-06-04T01:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nR9ua+2TUIQkx6rqeyNypHmw+5M7SBAS2Gxguj4JfwA+h2Tm4vONf2hecbs0+RzgGHg8FQihR8f1S4NLpdMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:13:19.476478Z"},"content_sha256":"4adfbdbe9a0c56c2751cba55b4db1244a01b759e5b4ad17595bd306f750a70cb","schema_version":"1.0","event_id":"sha256:4adfbdbe9a0c56c2751cba55b4db1244a01b759e5b4ad17595bd306f750a70cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3EDN5WG4PVBS33UAULFFZNSN7/bundle.json","state_url":"https://pith.science/pith/R3EDN5WG4PVBS33UAULFFZNSN7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3EDN5WG4PVBS33UAULFFZNSN7/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":"2026-06-29T09:13:19Z","links":{"resolver":"https://pith.science/pith/R3EDN5WG4PVBS33UAULFFZNSN7","bundle":"https://pith.science/pith/R3EDN5WG4PVBS33UAULFFZNSN7/bundle.json","state":"https://pith.science/pith/R3EDN5WG4PVBS33UAULFFZNSN7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3EDN5WG4PVBS33UAULFFZNSN7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R3EDN5WG4PVBS33UAULFFZNSN7","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":"25bfc167a06dc2f918796a8b18c3a944045f2a4bbb7fddcc63c16fbec9c7b69f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:20:48Z","title_canon_sha256":"9f358387fbb2e6f74c96bb08b4c1084022b0fb46dc36ab3235fefc8afef7a348"},"schema_version":"1.0","source":{"id":"2606.05116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05116","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05116v1","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05116","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"R3EDN5WG4PVB","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"R3EDN5WG4PVBS33U","created_at":"2026-06-04T01:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"R3EDN5WG","created_at":"2026-06-04T01:10:06Z"}],"graph_snapshots":[{"event_id":"sha256:4adfbdbe9a0c56c2751cba55b4db1244a01b759e5b4ad17595bd306f750a70cb","target":"graph","created_at":"2026-06-04T01:10:06Z","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/2606.05116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure. Existing architectures, including DeepSets and SetTransformer, require pre-encoded graph embeddings from a separate GNN, creating a bottleneck between feature extraction and set-level contextualisation. In contrast, GST interleaves node-level feature propagation and cross-graph contextual modelling at every layer, fusing the two levels of information through a gating mechanism. We e","authors_text":"Baoquan Chen, Daniel Probst, Jose E. Escrig Molina","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:20:48Z","title":"Graph Set Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05116","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:ec3855bb974449b25856453c95afebbd8e6eff69d314066eba81aa3b5e1b49c6","target":"record","created_at":"2026-06-04T01:10:06Z","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":"25bfc167a06dc2f918796a8b18c3a944045f2a4bbb7fddcc63c16fbec9c7b69f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:20:48Z","title_canon_sha256":"9f358387fbb2e6f74c96bb08b4c1084022b0fb46dc36ab3235fefc8afef7a348"},"schema_version":"1.0","source":{"id":"2606.05116","kind":"arxiv","version":1}},"canonical_sha256":"8ec836f6c6e3ea196f74051652e5b26ff8c2e64ddb0a3d181574efbaa9eec9a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ec836f6c6e3ea196f74051652e5b26ff8c2e64ddb0a3d181574efbaa9eec9a4","first_computed_at":"2026-06-04T01:10:06.913282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:10:06.913282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ap8VFgEJODSp+TGgeWn+eQVQYaj6w6qqN6b6NOmG5t55tSGyu7nySCTZG1fh/AVhBbcIr66WeAjWgzDKqIUkDg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:10:06.913916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec3855bb974449b25856453c95afebbd8e6eff69d314066eba81aa3b5e1b49c6","sha256:4adfbdbe9a0c56c2751cba55b4db1244a01b759e5b4ad17595bd306f750a70cb"],"state_sha256":"9c076c98cf1834f4929807d46b86668cb66369865d6282533f8d965793bfb089"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skUDh+d0380UA6V/DFnT0EtkUbGl9X+ssXCMCm9BeZfX08BZdRxgt+2GYHX7LVvVV2R3WdrJTaZVdNSwYMtbCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T09:13:19.478513Z","bundle_sha256":"605ce99c6026f97b3ff347c24e7bb9e66ef8ea10128d4b5f35a6960245334ba4"}}