{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3VXTGERRTJFKALZBXR6RFATSNF","short_pith_number":"pith:3VXTGERR","schema_version":"1.0","canonical_sha256":"dd6f3312319a4aa02f21bc7d128272697f34efea48bfeb77ec1db166c641dfa9","source":{"kind":"arxiv","id":"2505.19445","version":1},"attestation_state":"computed","paper":{"title":"MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hari Shankar, Ponnurangam Kumaraguru, Rishabh Bhattacharya, Vaishnavi Shivkumar","submitted_at":"2025-05-26T03:07:58Z","abstract_excerpt":"The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph Multi-linear Networks (GMT) have emerged, they remain vulnerable to generating explanations based on spurious correlations, potentially undermining trust in critical applications. We present MetaGMT, a meta-learning framework that enhances explanation fidelity through a novel bi-level optimization approach. We demonstrate that MetaGMT significantly improves both expla"},"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":"2505.19445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T03:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"cf7a6aeea0391790cb82449d7f85d99951ff511031e77d0c709d34098d8e151a","abstract_canon_sha256":"c2db9321335831df4c07fb59c6329fbfd63bcf77e80288a92cc8e86fafdf0093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:30.394686Z","signature_b64":"PpCmeLIcEWAMVEvKGUQt8Fv+kUUjadWsrkfJ2Qokuve3No6gne8yASZmTNKmV79dh0LphskEkxw1+4zWRCVcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd6f3312319a4aa02f21bc7d128272697f34efea48bfeb77ec1db166c641dfa9","last_reissued_at":"2026-07-05T11:09:30.394195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:30.394195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hari Shankar, Ponnurangam Kumaraguru, Rishabh Bhattacharya, Vaishnavi Shivkumar","submitted_at":"2025-05-26T03:07:58Z","abstract_excerpt":"The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph Multi-linear Networks (GMT) have emerged, they remain vulnerable to generating explanations based on spurious correlations, potentially undermining trust in critical applications. We present MetaGMT, a meta-learning framework that enhances explanation fidelity through a novel bi-level optimization approach. We demonstrate that MetaGMT significantly improves both expla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19445","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/2505.19445/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":"2505.19445","created_at":"2026-07-05T11:09:30.394252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19445v1","created_at":"2026-07-05T11:09:30.394252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19445","created_at":"2026-07-05T11:09:30.394252+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VXTGERRTJFK","created_at":"2026-07-05T11:09:30.394252+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VXTGERRTJFKALZB","created_at":"2026-07-05T11:09:30.394252+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VXTGERR","created_at":"2026-07-05T11:09:30.394252+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/3VXTGERRTJFKALZBXR6RFATSNF","json":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF.json","graph_json":"https://pith.science/api/pith-number/3VXTGERRTJFKALZBXR6RFATSNF/graph.json","events_json":"https://pith.science/api/pith-number/3VXTGERRTJFKALZBXR6RFATSNF/events.json","paper":"https://pith.science/paper/3VXTGERR"},"agent_actions":{"view_html":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF","download_json":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF.json","view_paper":"https://pith.science/paper/3VXTGERR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19445&json=true","fetch_graph":"https://pith.science/api/pith-number/3VXTGERRTJFKALZBXR6RFATSNF/graph.json","fetch_events":"https://pith.science/api/pith-number/3VXTGERRTJFKALZBXR6RFATSNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF/action/storage_attestation","attest_author":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF/action/author_attestation","sign_citation":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF/action/citation_signature","submit_replication":"https://pith.science/pith/3VXTGERRTJFKALZBXR6RFATSNF/action/replication_record"}},"created_at":"2026-07-05T11:09:30.394252+00:00","updated_at":"2026-07-05T11:09:30.394252+00:00"}