{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VE53QJ6FV5CJKHT65GOMPBYO6G","short_pith_number":"pith:VE53QJ6F","schema_version":"1.0","canonical_sha256":"a93bb827c5af44951e7ee99cc7870ef19521aa565dc58a31d209ea9f9a8570d8","source":{"kind":"arxiv","id":"2507.05110","version":3},"attestation_state":"computed","paper":{"title":"Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haoxiang Cheng, Hao Zou, Peng Cui, Shixuan Liu, Wenjing Yang, Yue He, Yunfei Wang, Zhong Liu","submitted_at":"2025-07-07T15:27:48Z","abstract_excerpt":"Logical rule learning, a prominent category of knowledge graph (KG) reasoning methods, constitutes a critical research area aimed at learning explicit rules from observed facts to infer missing knowledge. However, like all KG reasoning methods, rule learning suffers from a critical weakness-its dependence on the I.I.D. assumption. This assumption can easily be violated due to selection bias during training or agnostic distribution shifts during testing (e.g., as in query shift scenarios), ultimately undermining model performance and reliability. To enable robust KG reasoning in wild environmen"},"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":"2507.05110","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T15:27:48Z","cross_cats_sorted":[],"title_canon_sha256":"e9d87c2925f8386f1f866af9e183baea543d71c3f9f7f270b4c5ff2fed50ccdc","abstract_canon_sha256":"d3b2d0b47814bc8978208485dcdc214a9e7782eb69c15e1d52d4d0f12c9249fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:53.513233Z","signature_b64":"fZa9L3KEp5wDKbaHC6NymWNrK1/ok1XnjioODY6gbhOGrUlOZZrHZMwJA2Z4if66TLM8Cn4uuWUeg12ecNMzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a93bb827c5af44951e7ee99cc7870ef19521aa565dc58a31d209ea9f9a8570d8","last_reissued_at":"2026-07-05T11:34:53.512758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:53.512758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haoxiang Cheng, Hao Zou, Peng Cui, Shixuan Liu, Wenjing Yang, Yue He, Yunfei Wang, Zhong Liu","submitted_at":"2025-07-07T15:27:48Z","abstract_excerpt":"Logical rule learning, a prominent category of knowledge graph (KG) reasoning methods, constitutes a critical research area aimed at learning explicit rules from observed facts to infer missing knowledge. However, like all KG reasoning methods, rule learning suffers from a critical weakness-its dependence on the I.I.D. assumption. This assumption can easily be violated due to selection bias during training or agnostic distribution shifts during testing (e.g., as in query shift scenarios), ultimately undermining model performance and reliability. To enable robust KG reasoning in wild environmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05110","kind":"arxiv","version":3},"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/2507.05110/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":"2507.05110","created_at":"2026-07-05T11:34:53.512817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05110v3","created_at":"2026-07-05T11:34:53.512817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05110","created_at":"2026-07-05T11:34:53.512817+00:00"},{"alias_kind":"pith_short_12","alias_value":"VE53QJ6FV5CJ","created_at":"2026-07-05T11:34:53.512817+00:00"},{"alias_kind":"pith_short_16","alias_value":"VE53QJ6FV5CJKHT6","created_at":"2026-07-05T11:34:53.512817+00:00"},{"alias_kind":"pith_short_8","alias_value":"VE53QJ6F","created_at":"2026-07-05T11:34:53.512817+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/VE53QJ6FV5CJKHT65GOMPBYO6G","json":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G.json","graph_json":"https://pith.science/api/pith-number/VE53QJ6FV5CJKHT65GOMPBYO6G/graph.json","events_json":"https://pith.science/api/pith-number/VE53QJ6FV5CJKHT65GOMPBYO6G/events.json","paper":"https://pith.science/paper/VE53QJ6F"},"agent_actions":{"view_html":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G","download_json":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G.json","view_paper":"https://pith.science/paper/VE53QJ6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05110&json=true","fetch_graph":"https://pith.science/api/pith-number/VE53QJ6FV5CJKHT65GOMPBYO6G/graph.json","fetch_events":"https://pith.science/api/pith-number/VE53QJ6FV5CJKHT65GOMPBYO6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G/action/storage_attestation","attest_author":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G/action/author_attestation","sign_citation":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G/action/citation_signature","submit_replication":"https://pith.science/pith/VE53QJ6FV5CJKHT65GOMPBYO6G/action/replication_record"}},"created_at":"2026-07-05T11:34:53.512817+00:00","updated_at":"2026-07-05T11:34:53.512817+00:00"}