{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RDUEB2CBAV3KLILRBL7LOXTCKU","short_pith_number":"pith:RDUEB2CB","schema_version":"1.0","canonical_sha256":"88e840e8410576a5a1710afeb75e6255000aa783ce7e7086eadbbbb812c8063e","source":{"kind":"arxiv","id":"2202.08388","version":1},"attestation_state":"computed","paper":{"title":"Generalizable Information Theoretic Causal Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furui Liu, Jianye Hao, Jun Wang, Mengyue Yang, Xinyu Cai, Xu Chen, Zhitang Chen","submitted_at":"2022-02-17T00:38:35Z","abstract_excerpt":"It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing the correlation (or its proxy) between features and the downstream task (labels), which typically results in a representation containing cause, effect and spurious correlated variables of the label. Its generalizability may deteriorate because of the unstability of the non-causal parts. In this paper, we propose to learn causal representation from observati"},"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":"2202.08388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T00:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"2375a205e3aa9533b73a0bb5375d7d48ad1f0f4bf80a9dc370aa72a689b1db67","abstract_canon_sha256":"656d468dccfb541e3c66b43dddce1b0d8294c4c3a130d6eeac89f223bf822ed1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:45.345151Z","signature_b64":"i4bOn+mdzgQ/yxMIlm0qQfUSzBCZkaxw2ogkCfki/TKTH/Li0UYPL9qLRx0O2m0A7yOElrrQXs55VpAXy8jEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88e840e8410576a5a1710afeb75e6255000aa783ce7e7086eadbbbb812c8063e","last_reissued_at":"2026-07-05T03:57:45.344652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:45.344652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizable Information Theoretic Causal Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furui Liu, Jianye Hao, Jun Wang, Mengyue Yang, Xinyu Cai, Xu Chen, Zhitang Chen","submitted_at":"2022-02-17T00:38:35Z","abstract_excerpt":"It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing the correlation (or its proxy) between features and the downstream task (labels), which typically results in a representation containing cause, effect and spurious correlated variables of the label. Its generalizability may deteriorate because of the unstability of the non-causal parts. In this paper, we propose to learn causal representation from observati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08388","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/2202.08388/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":"2202.08388","created_at":"2026-07-05T03:57:45.344711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08388v1","created_at":"2026-07-05T03:57:45.344711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08388","created_at":"2026-07-05T03:57:45.344711+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDUEB2CBAV3K","created_at":"2026-07-05T03:57:45.344711+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDUEB2CBAV3KLILR","created_at":"2026-07-05T03:57:45.344711+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDUEB2CB","created_at":"2026-07-05T03:57:45.344711+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/RDUEB2CBAV3KLILRBL7LOXTCKU","json":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU.json","graph_json":"https://pith.science/api/pith-number/RDUEB2CBAV3KLILRBL7LOXTCKU/graph.json","events_json":"https://pith.science/api/pith-number/RDUEB2CBAV3KLILRBL7LOXTCKU/events.json","paper":"https://pith.science/paper/RDUEB2CB"},"agent_actions":{"view_html":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU","download_json":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU.json","view_paper":"https://pith.science/paper/RDUEB2CB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08388&json=true","fetch_graph":"https://pith.science/api/pith-number/RDUEB2CBAV3KLILRBL7LOXTCKU/graph.json","fetch_events":"https://pith.science/api/pith-number/RDUEB2CBAV3KLILRBL7LOXTCKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU/action/storage_attestation","attest_author":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU/action/author_attestation","sign_citation":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU/action/citation_signature","submit_replication":"https://pith.science/pith/RDUEB2CBAV3KLILRBL7LOXTCKU/action/replication_record"}},"created_at":"2026-07-05T03:57:45.344711+00:00","updated_at":"2026-07-05T03:57:45.344711+00:00"}