{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QZHI6QNVUNIS2BDAMHODYDB6HE","short_pith_number":"pith:QZHI6QNV","schema_version":"1.0","canonical_sha256":"864e8f41b5a3512d046061dc3c0c3e392e37311ddc02b80b703c2eae91a1312c","source":{"kind":"arxiv","id":"2206.02886","version":2},"attestation_state":"computed","paper":{"title":"Graph Rationalization with Environment-based Augmentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Liu, Jiaxin Xu, Meng Jiang, Tengfei Luo, Tong Zhao","submitted_at":"2022-06-06T20:23:30Z","abstract_excerpt":"Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data. In graph applications such as molecule and polymer property prediction, identifying representative subgraph structures named as graph rationales plays an essential role in the performance of graph neural networks. Existing graph pooling and/or distribution intervention methods suffer from lack of examples to learn to identify optimal graph ratio"},"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":"2206.02886","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:23:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fd9c4941ecbe36af2b6b7c2675c5113ecad24cf4a66c13a3810d595865451c0","abstract_canon_sha256":"f907ccae8d34e83762d42a67f665269f79512ff0f1e4c404d347ab93b6de9e25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:42.962461Z","signature_b64":"mDHavOw2qlRLG71aeC4nYWXvQ13C+QYn53GFCAPqSf9VKVWQx/ENT8bGQM9LGduZL/lEYEZQvhdym5+JYJSUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864e8f41b5a3512d046061dc3c0c3e392e37311ddc02b80b703c2eae91a1312c","last_reissued_at":"2026-07-05T05:00:42.962065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:42.962065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Rationalization with Environment-based Augmentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Liu, Jiaxin Xu, Meng Jiang, Tengfei Luo, Tong Zhao","submitted_at":"2022-06-06T20:23:30Z","abstract_excerpt":"Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data. In graph applications such as molecule and polymer property prediction, identifying representative subgraph structures named as graph rationales plays an essential role in the performance of graph neural networks. Existing graph pooling and/or distribution intervention methods suffer from lack of examples to learn to identify optimal graph ratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02886","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/2206.02886/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":"2206.02886","created_at":"2026-07-05T05:00:42.962121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02886v2","created_at":"2026-07-05T05:00:42.962121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02886","created_at":"2026-07-05T05:00:42.962121+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZHI6QNVUNIS","created_at":"2026-07-05T05:00:42.962121+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZHI6QNVUNIS2BDA","created_at":"2026-07-05T05:00:42.962121+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZHI6QNV","created_at":"2026-07-05T05:00:42.962121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12226","citing_title":"Learning Causality for Modern Machine Learning","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE","json":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE.json","graph_json":"https://pith.science/api/pith-number/QZHI6QNVUNIS2BDAMHODYDB6HE/graph.json","events_json":"https://pith.science/api/pith-number/QZHI6QNVUNIS2BDAMHODYDB6HE/events.json","paper":"https://pith.science/paper/QZHI6QNV"},"agent_actions":{"view_html":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE","download_json":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE.json","view_paper":"https://pith.science/paper/QZHI6QNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02886&json=true","fetch_graph":"https://pith.science/api/pith-number/QZHI6QNVUNIS2BDAMHODYDB6HE/graph.json","fetch_events":"https://pith.science/api/pith-number/QZHI6QNVUNIS2BDAMHODYDB6HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE/action/storage_attestation","attest_author":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE/action/author_attestation","sign_citation":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE/action/citation_signature","submit_replication":"https://pith.science/pith/QZHI6QNVUNIS2BDAMHODYDB6HE/action/replication_record"}},"created_at":"2026-07-05T05:00:42.962121+00:00","updated_at":"2026-07-05T05:00:42.962121+00:00"}