{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BY6BZKEFZJ6WQ7YU3FS7H2I7O3","short_pith_number":"pith:BY6BZKEF","schema_version":"1.0","canonical_sha256":"0e3c1ca885ca7d687f14d965f3e91f76ea28c25442c4bfeef30c1ecfda8e2a3b","source":{"kind":"arxiv","id":"2606.01176","version":1},"attestation_state":"computed","paper":{"title":"Temporal Motif Signatures for Temporal Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dylan Sandfelder, Mihai Cucuringu, Xiaowen Dong","submitted_at":"2026-05-31T11:32:32Z","abstract_excerpt":"Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow -- that vanilla temporal graph neural networks (TGNNs) often fail to expose to their edge scorers. We show this concretely on MOOC interaction prediction, where a small four-feature family of past-window star counts already delivers most of the lift over a strong static GNN. Across a wide set of real and synthetic temporal datasets we find that motif activity organizes consistently along three scale-stable axes (dyadic recency/reciprocity, star d"},"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":"2606.01176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T11:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"22b92540c47ffacef3dd5d3258c3f15bb65d8629cf4fa90241e15eb0a39d25ba","abstract_canon_sha256":"6f0de2752ee4aabdaa3a6c369e86cd28a13acd9557448ac092b35a1f841829c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:25.845929Z","signature_b64":"tqCI0MGRKVmAoB8ESbAp31XC4OUwR0RazDhgcxXefX5OT7Jps7uHhFYWg1eNJSxgK75hoVZfReou8SUmmZbxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e3c1ca885ca7d687f14d965f3e91f76ea28c25442c4bfeef30c1ecfda8e2a3b","last_reissued_at":"2026-06-02T02:04:25.845490Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:25.845490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Motif Signatures for Temporal Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dylan Sandfelder, Mihai Cucuringu, Xiaowen Dong","submitted_at":"2026-05-31T11:32:32Z","abstract_excerpt":"Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow -- that vanilla temporal graph neural networks (TGNNs) often fail to expose to their edge scorers. We show this concretely on MOOC interaction prediction, where a small four-feature family of past-window star counts already delivers most of the lift over a strong static GNN. Across a wide set of real and synthetic temporal datasets we find that motif activity organizes consistently along three scale-stable axes (dyadic recency/reciprocity, star d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01176","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/2606.01176/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":"2606.01176","created_at":"2026-06-02T02:04:25.845552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01176v1","created_at":"2026-06-02T02:04:25.845552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01176","created_at":"2026-06-02T02:04:25.845552+00:00"},{"alias_kind":"pith_short_12","alias_value":"BY6BZKEFZJ6W","created_at":"2026-06-02T02:04:25.845552+00:00"},{"alias_kind":"pith_short_16","alias_value":"BY6BZKEFZJ6WQ7YU","created_at":"2026-06-02T02:04:25.845552+00:00"},{"alias_kind":"pith_short_8","alias_value":"BY6BZKEF","created_at":"2026-06-02T02:04:25.845552+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/BY6BZKEFZJ6WQ7YU3FS7H2I7O3","json":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3.json","graph_json":"https://pith.science/api/pith-number/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/graph.json","events_json":"https://pith.science/api/pith-number/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/events.json","paper":"https://pith.science/paper/BY6BZKEF"},"agent_actions":{"view_html":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3","download_json":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3.json","view_paper":"https://pith.science/paper/BY6BZKEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01176&json=true","fetch_graph":"https://pith.science/api/pith-number/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/graph.json","fetch_events":"https://pith.science/api/pith-number/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/action/storage_attestation","attest_author":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/action/author_attestation","sign_citation":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/action/citation_signature","submit_replication":"https://pith.science/pith/BY6BZKEFZJ6WQ7YU3FS7H2I7O3/action/replication_record"}},"created_at":"2026-06-02T02:04:25.845552+00:00","updated_at":"2026-06-02T02:04:25.845552+00:00"}