{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3PRQLTTV4IYALXNPG64NU5OK3T","short_pith_number":"pith:3PRQLTTV","schema_version":"1.0","canonical_sha256":"dbe305ce75e23005ddaf37b8da75cadcca4eaad8addef8229d73b9713e2e3c0a","source":{"kind":"arxiv","id":"2203.15209","version":1},"attestation_state":"computed","paper":{"title":"OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baochun Li, Hao Lan, Hao Wang, Wanyu Lin","submitted_at":"2022-03-29T03:08:33Z","abstract_excerpt":"This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as c"},"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":"2203.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-29T03:08:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cfd770494bd88a608262b05053b90e707cbd5d8026d7010b78203233212b0e21","abstract_canon_sha256":"6c501aaca8c24eeea5e31960457ca9288a6e1ddd06b1eed7184c0f4e6fb9396f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:14.502592Z","signature_b64":"WzFDhhY11fzHYXnFrISxNoTiisK2sqFwecIOh36g3ZJbE9M7ZAV8hQDldiMB4VrMtGXlTOsU5zVi8sdhbEx7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe305ce75e23005ddaf37b8da75cadcca4eaad8addef8229d73b9713e2e3c0a","last_reissued_at":"2026-07-05T04:13:14.502168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:14.502168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baochun Li, Hao Lan, Hao Wang, Wanyu Lin","submitted_at":"2022-03-29T03:08:33Z","abstract_excerpt":"This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15209","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/2203.15209/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":"2203.15209","created_at":"2026-07-05T04:13:14.502227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15209v1","created_at":"2026-07-05T04:13:14.502227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15209","created_at":"2026-07-05T04:13:14.502227+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PRQLTTV4IYA","created_at":"2026-07-05T04:13:14.502227+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PRQLTTV4IYALXNP","created_at":"2026-07-05T04:13:14.502227+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PRQLTTV","created_at":"2026-07-05T04:13:14.502227+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/3PRQLTTV4IYALXNPG64NU5OK3T","json":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T.json","graph_json":"https://pith.science/api/pith-number/3PRQLTTV4IYALXNPG64NU5OK3T/graph.json","events_json":"https://pith.science/api/pith-number/3PRQLTTV4IYALXNPG64NU5OK3T/events.json","paper":"https://pith.science/paper/3PRQLTTV"},"agent_actions":{"view_html":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T","download_json":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T.json","view_paper":"https://pith.science/paper/3PRQLTTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15209&json=true","fetch_graph":"https://pith.science/api/pith-number/3PRQLTTV4IYALXNPG64NU5OK3T/graph.json","fetch_events":"https://pith.science/api/pith-number/3PRQLTTV4IYALXNPG64NU5OK3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T/action/storage_attestation","attest_author":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T/action/author_attestation","sign_citation":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T/action/citation_signature","submit_replication":"https://pith.science/pith/3PRQLTTV4IYALXNPG64NU5OK3T/action/replication_record"}},"created_at":"2026-07-05T04:13:14.502227+00:00","updated_at":"2026-07-05T04:13:14.502227+00:00"}