{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OX2LDMF43GQJKOECURSXZ7GKAX","short_pith_number":"pith:OX2LDMF4","schema_version":"1.0","canonical_sha256":"75f4b1b0bcd9a0953882a4657cfcca05d3dfa8526de3b2fb8ea4ae523b520e87","source":{"kind":"arxiv","id":"2506.17718","version":2},"attestation_state":"computed","paper":{"title":"Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Li, Jian Liang, Kun Gai, Longhui Yuan, Shuang Li, Wenze Song, Zhuo He","submitted_at":"2025-06-21T14:05:37Z","abstract_excerpt":"Endowing deep models with the ability to generalize in dynamic scenarios is of vital significance for real-world deployment, given the continuous and complex changes in data distribution. Recently, evolving domain generalization (EDG) has emerged to address distribution shifts over time, aiming to capture evolving patterns for improved model generalization. However, existing EDG methods may suffer from spurious correlations by modeling only the dependence between data and targets across domains, creating a shortcut between task-irrelevant factors and the target, which hinders generalization. T"},"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":"2506.17718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T14:05:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b325863a2d8739757e4a01136b930ddea088d101d34f274b2f443f9736d01b93","abstract_canon_sha256":"182a46f9aba4c61128162726764ea6f2be1fa05e6c515bcdc4da54e7e78459dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:37.912415Z","signature_b64":"tb/Sk1RePFihfUYPryRx0ZPn+xjiOqoacajsoGpMNtpdskaHAv1pC1uJDBbI7cKkFeB+5iT5Kx0QvCAnQu5QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75f4b1b0bcd9a0953882a4657cfcca05d3dfa8526de3b2fb8ea4ae523b520e87","last_reissued_at":"2026-07-05T11:28:37.911856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:37.911856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Li, Jian Liang, Kun Gai, Longhui Yuan, Shuang Li, Wenze Song, Zhuo He","submitted_at":"2025-06-21T14:05:37Z","abstract_excerpt":"Endowing deep models with the ability to generalize in dynamic scenarios is of vital significance for real-world deployment, given the continuous and complex changes in data distribution. Recently, evolving domain generalization (EDG) has emerged to address distribution shifts over time, aiming to capture evolving patterns for improved model generalization. However, existing EDG methods may suffer from spurious correlations by modeling only the dependence between data and targets across domains, creating a shortcut between task-irrelevant factors and the target, which hinders generalization. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17718","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/2506.17718/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":"2506.17718","created_at":"2026-07-05T11:28:37.911917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17718v2","created_at":"2026-07-05T11:28:37.911917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17718","created_at":"2026-07-05T11:28:37.911917+00:00"},{"alias_kind":"pith_short_12","alias_value":"OX2LDMF43GQJ","created_at":"2026-07-05T11:28:37.911917+00:00"},{"alias_kind":"pith_short_16","alias_value":"OX2LDMF43GQJKOEC","created_at":"2026-07-05T11:28:37.911917+00:00"},{"alias_kind":"pith_short_8","alias_value":"OX2LDMF4","created_at":"2026-07-05T11:28:37.911917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01295","citing_title":"Autonomous Drift Learning in Data Streams: A Unified Perspective","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX","json":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX.json","graph_json":"https://pith.science/api/pith-number/OX2LDMF43GQJKOECURSXZ7GKAX/graph.json","events_json":"https://pith.science/api/pith-number/OX2LDMF43GQJKOECURSXZ7GKAX/events.json","paper":"https://pith.science/paper/OX2LDMF4"},"agent_actions":{"view_html":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX","download_json":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX.json","view_paper":"https://pith.science/paper/OX2LDMF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17718&json=true","fetch_graph":"https://pith.science/api/pith-number/OX2LDMF43GQJKOECURSXZ7GKAX/graph.json","fetch_events":"https://pith.science/api/pith-number/OX2LDMF43GQJKOECURSXZ7GKAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX/action/storage_attestation","attest_author":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX/action/author_attestation","sign_citation":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX/action/citation_signature","submit_replication":"https://pith.science/pith/OX2LDMF43GQJKOECURSXZ7GKAX/action/replication_record"}},"created_at":"2026-07-05T11:28:37.911917+00:00","updated_at":"2026-07-05T11:28:37.911917+00:00"}