{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EA66I2JFHFPXC6SZWCCSIVFQJI","short_pith_number":"pith:EA66I2JF","schema_version":"1.0","canonical_sha256":"203de46925395f717a59b0852454b04a1539214657ea80d442371f0b05014f14","source":{"kind":"arxiv","id":"2502.17912","version":2},"attestation_state":"computed","paper":{"title":"Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jing Tang, Pengwen Dai, Xiaochun Cao, Yifan Song, Yihong Luo, Yuhan Chen","submitted_at":"2025-02-25T07:20:00Z","abstract_excerpt":"Despite extensive research efforts focused on OOD detection on images, OOD detection on nodes in graph learning remains underexplored. The dependence among graph nodes hinders the trivial adaptation of existing approaches on images that assume inputs to be i.i.d. sampled, since many unique features and challenges specific to graphs are not considered, such as the heterophily issue. Recently, GNNSafe, which considers node dependence, adapted energy-based detection to the graph domain with state-of-the-art performance, however, it has two serious issues: 1) it derives node energy from classifica"},"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":"2502.17912","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:20:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a49784a20061753edadb8e8cf5dc5264448d6c6d58df385fee36e53f46011a62","abstract_canon_sha256":"686570c231bacdbcf8369d1164ec349d3d0cf67c91ec106c8d6db0d431395dd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:39.548969Z","signature_b64":"83WB+l9Q0sGqEseSp0OPe8s9o5m5ILUBw6XMIiEJmInIjoJdbCEWxKxK+BSHyFxxRGXRejqhIecXCY6o27cbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"203de46925395f717a59b0852454b04a1539214657ea80d442371f0b05014f14","last_reissued_at":"2026-07-05T10:32:39.548276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:39.548276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jing Tang, Pengwen Dai, Xiaochun Cao, Yifan Song, Yihong Luo, Yuhan Chen","submitted_at":"2025-02-25T07:20:00Z","abstract_excerpt":"Despite extensive research efforts focused on OOD detection on images, OOD detection on nodes in graph learning remains underexplored. The dependence among graph nodes hinders the trivial adaptation of existing approaches on images that assume inputs to be i.i.d. sampled, since many unique features and challenges specific to graphs are not considered, such as the heterophily issue. Recently, GNNSafe, which considers node dependence, adapted energy-based detection to the graph domain with state-of-the-art performance, however, it has two serious issues: 1) it derives node energy from classifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17912","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/2502.17912/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":"2502.17912","created_at":"2026-07-05T10:32:39.548381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17912v2","created_at":"2026-07-05T10:32:39.548381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17912","created_at":"2026-07-05T10:32:39.548381+00:00"},{"alias_kind":"pith_short_12","alias_value":"EA66I2JFHFPX","created_at":"2026-07-05T10:32:39.548381+00:00"},{"alias_kind":"pith_short_16","alias_value":"EA66I2JFHFPXC6SZ","created_at":"2026-07-05T10:32:39.548381+00:00"},{"alias_kind":"pith_short_8","alias_value":"EA66I2JF","created_at":"2026-07-05T10:32:39.548381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.06356","citing_title":"Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI","json":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI.json","graph_json":"https://pith.science/api/pith-number/EA66I2JFHFPXC6SZWCCSIVFQJI/graph.json","events_json":"https://pith.science/api/pith-number/EA66I2JFHFPXC6SZWCCSIVFQJI/events.json","paper":"https://pith.science/paper/EA66I2JF"},"agent_actions":{"view_html":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI","download_json":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI.json","view_paper":"https://pith.science/paper/EA66I2JF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17912&json=true","fetch_graph":"https://pith.science/api/pith-number/EA66I2JFHFPXC6SZWCCSIVFQJI/graph.json","fetch_events":"https://pith.science/api/pith-number/EA66I2JFHFPXC6SZWCCSIVFQJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI/action/storage_attestation","attest_author":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI/action/author_attestation","sign_citation":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI/action/citation_signature","submit_replication":"https://pith.science/pith/EA66I2JFHFPXC6SZWCCSIVFQJI/action/replication_record"}},"created_at":"2026-07-05T10:32:39.548381+00:00","updated_at":"2026-07-05T10:32:39.548381+00:00"}