{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2FVIHD7RD27XLD7IISFHX6OAJ4","short_pith_number":"pith:2FVIHD7R","schema_version":"1.0","canonical_sha256":"d16a838ff11ebf758fe8448a7bf9c04f0e347a21f1605d39ad297f920388756e","source":{"kind":"arxiv","id":"2602.23135","version":2},"attestation_state":"computed","paper":{"title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Marek Rei, Tyler Bonnet","submitted_at":"2026-02-26T15:51:51Z","abstract_excerpt":"Edge classification on directed dynamic graphs requires modeling interactions between source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for processing source and destination nodes, with limited or no systematic role-aware modeling. We propose DyGnROLE (Dynamic Graph Node-Role-Oriented Latent Encoding), a Transformer-based architecture that disentangles source and destination representations. By using separate embedding tables and role-semantic positional encodings, the "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.23135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T15:51:51Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"1e83c3decf89641ccb16913d936643537b5146e9794a834e1c16926f0c7d311b","abstract_canon_sha256":"a1942617e48d35188aff8d7f280efc0ca59f65b23b82b72e8fe60abc7ff09c92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:28.577014Z","signature_b64":"c/zmzt8LcSClgXTVR30LLavNxOr0ll8kIGqfMIyP/aAIeBttKs9wfSrvN9j8GysSNbkz77GRQzJI7kKIviN8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16a838ff11ebf758fe8448a7bf9c04f0e347a21f1605d39ad297f920388756e","last_reissued_at":"2026-06-30T01:16:28.576422Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:28.576422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Marek Rei, Tyler Bonnet","submitted_at":"2026-02-26T15:51:51Z","abstract_excerpt":"Edge classification on directed dynamic graphs requires modeling interactions between source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for processing source and destination nodes, with limited or no systematic role-aware modeling. We propose DyGnROLE (Dynamic Graph Node-Role-Oriented Latent Encoding), a Transformer-based architecture that disentangles source and destination representations. By using separate embedding tables and role-semantic positional encodings, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23135","kind":"arxiv","version":2},"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/2602.23135/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.23135","created_at":"2026-06-30T01:16:28.576483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23135v2","created_at":"2026-06-30T01:16:28.576483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23135","created_at":"2026-06-30T01:16:28.576483+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FVIHD7RD27X","created_at":"2026-06-30T01:16:28.576483+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FVIHD7RD27XLD7I","created_at":"2026-06-30T01:16:28.576483+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FVIHD7R","created_at":"2026-06-30T01:16:28.576483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4","json":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4.json","graph_json":"https://pith.science/api/pith-number/2FVIHD7RD27XLD7IISFHX6OAJ4/graph.json","events_json":"https://pith.science/api/pith-number/2FVIHD7RD27XLD7IISFHX6OAJ4/events.json","paper":"https://pith.science/paper/2FVIHD7R"},"agent_actions":{"view_html":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4","download_json":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4.json","view_paper":"https://pith.science/paper/2FVIHD7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23135&json=true","fetch_graph":"https://pith.science/api/pith-number/2FVIHD7RD27XLD7IISFHX6OAJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/2FVIHD7RD27XLD7IISFHX6OAJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4/action/storage_attestation","attest_author":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4/action/author_attestation","sign_citation":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4/action/citation_signature","submit_replication":"https://pith.science/pith/2FVIHD7RD27XLD7IISFHX6OAJ4/action/replication_record"}},"created_at":"2026-06-30T01:16:28.576483+00:00","updated_at":"2026-06-30T01:16:28.576483+00:00"}