{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:26ZDM7BWNIKQBAULFA747WFECQ","short_pith_number":"pith:26ZDM7BW","schema_version":"1.0","canonical_sha256":"d7b2367c366a1500828b283fcfd8a41416003ba282241ad9ac3d90da16ade6ee","source":{"kind":"arxiv","id":"2508.01925","version":1},"attestation_state":"computed","paper":{"title":"From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Hojat Allah Salehi, Jingchao Ni, Xu Zheng, Zhuomin Chen","submitted_at":"2025-08-03T21:19:58Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved remarkable performance in a wide range of graph-related learning tasks. However, explaining their predictions remains a challenging problem, especially due to the mismatch between the graphs used during training and those encountered during explanation. Most existing methods optimize soft edge masks on weighted graphs to highlight important substructures, but these graphs differ from the unweighted graphs on which GNNs are trained. This distributional shift leads to unreliable gradients and degraded explanation quality, especially when generating smal"},"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":"2508.01925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T21:19:58Z","cross_cats_sorted":[],"title_canon_sha256":"c671cd429561759658e7d9f4c3b008aa667dd7972df88d9335bae666c3658bab","abstract_canon_sha256":"70272277b240a519185600af09c99c724c7545f0a7141db9c3f03a7f4bd88b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:48.260418Z","signature_b64":"yFAfoxD9UVHc2KWU9GVADzjwmJKsTCjUsUjeVaWa3ENA2DND2j3rDDyb3+l2trNdKL88oOivP/L9X509GxrGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b2367c366a1500828b283fcfd8a41416003ba282241ad9ac3d90da16ade6ee","last_reissued_at":"2026-07-05T11:47:48.259886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:48.259886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Hojat Allah Salehi, Jingchao Ni, Xu Zheng, Zhuomin Chen","submitted_at":"2025-08-03T21:19:58Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved remarkable performance in a wide range of graph-related learning tasks. However, explaining their predictions remains a challenging problem, especially due to the mismatch between the graphs used during training and those encountered during explanation. Most existing methods optimize soft edge masks on weighted graphs to highlight important substructures, but these graphs differ from the unweighted graphs on which GNNs are trained. This distributional shift leads to unreliable gradients and degraded explanation quality, especially when generating smal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01925","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/2508.01925/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":"2508.01925","created_at":"2026-07-05T11:47:48.259951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01925v1","created_at":"2026-07-05T11:47:48.259951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01925","created_at":"2026-07-05T11:47:48.259951+00:00"},{"alias_kind":"pith_short_12","alias_value":"26ZDM7BWNIKQ","created_at":"2026-07-05T11:47:48.259951+00:00"},{"alias_kind":"pith_short_16","alias_value":"26ZDM7BWNIKQBAUL","created_at":"2026-07-05T11:47:48.259951+00:00"},{"alias_kind":"pith_short_8","alias_value":"26ZDM7BW","created_at":"2026-07-05T11:47:48.259951+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/26ZDM7BWNIKQBAULFA747WFECQ","json":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ.json","graph_json":"https://pith.science/api/pith-number/26ZDM7BWNIKQBAULFA747WFECQ/graph.json","events_json":"https://pith.science/api/pith-number/26ZDM7BWNIKQBAULFA747WFECQ/events.json","paper":"https://pith.science/paper/26ZDM7BW"},"agent_actions":{"view_html":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ","download_json":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ.json","view_paper":"https://pith.science/paper/26ZDM7BW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01925&json=true","fetch_graph":"https://pith.science/api/pith-number/26ZDM7BWNIKQBAULFA747WFECQ/graph.json","fetch_events":"https://pith.science/api/pith-number/26ZDM7BWNIKQBAULFA747WFECQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ/action/storage_attestation","attest_author":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ/action/author_attestation","sign_citation":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ/action/citation_signature","submit_replication":"https://pith.science/pith/26ZDM7BWNIKQBAULFA747WFECQ/action/replication_record"}},"created_at":"2026-07-05T11:47:48.259951+00:00","updated_at":"2026-07-05T11:47:48.259951+00:00"}