{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J277QJRGY2RXWPXEEHY73DPEDV","short_pith_number":"pith:J277QJRG","schema_version":"1.0","canonical_sha256":"4ebff82626c6a37b3ee421f1fd8de41d6aeace47c08912a24b375267710579f3","source":{"kind":"arxiv","id":"2106.06607","version":2},"attestation_state":"computed","paper":{"title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Ethan Caballero, Ioannis Mitliagkas, Irina Rish, Jean-Christophe Gagnon-Audet, Kartik Ahuja, Yoshua Bengio","submitted_at":"2021-06-11T20:42:27Z","abstract_excerpt":"The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalization failures. Despite the promising theory, invariance principle-based approaches fail in common classification tasks, where invariant (causal) features capture all the information about the label. Are these failures due to the methods failing to capture the invariance? Or is the invariance principle itself insufficient? To answer these questions, we revisit the fundamental assumptions in linear regression tasks, where"},"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":"2106.06607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T20:42:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f612be1a85292c553c0aacff124431a2e90f701945cf0aeabbf7610c90fdd765","abstract_canon_sha256":"48e138e27895e68a347fa5f03fbbe883867ec2d7d4ecf3a9d02deb95ae598fc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:43.163124Z","signature_b64":"nQufnk0YQdakG6YGdz87y4QtLAgDfofk78/BOZSpSIHmmAh7H6rNXzkAjShP4v2WOeq801h2p9BJELj8QEYjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ebff82626c6a37b3ee421f1fd8de41d6aeace47c08912a24b375267710579f3","last_reissued_at":"2026-07-05T05:17:43.162701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:43.162701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Ethan Caballero, Ioannis Mitliagkas, Irina Rish, Jean-Christophe Gagnon-Audet, Kartik Ahuja, Yoshua Bengio","submitted_at":"2021-06-11T20:42:27Z","abstract_excerpt":"The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalization failures. Despite the promising theory, invariance principle-based approaches fail in common classification tasks, where invariant (causal) features capture all the information about the label. Are these failures due to the methods failing to capture the invariance? Or is the invariance principle itself insufficient? To answer these questions, we revisit the fundamental assumptions in linear regression tasks, where"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06607","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/2106.06607/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":"2106.06607","created_at":"2026-07-05T05:17:43.162765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06607v2","created_at":"2026-07-05T05:17:43.162765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06607","created_at":"2026-07-05T05:17:43.162765+00:00"},{"alias_kind":"pith_short_12","alias_value":"J277QJRGY2RX","created_at":"2026-07-05T05:17:43.162765+00:00"},{"alias_kind":"pith_short_16","alias_value":"J277QJRGY2RXWPXE","created_at":"2026-07-05T05:17:43.162765+00:00"},{"alias_kind":"pith_short_8","alias_value":"J277QJRG","created_at":"2026-07-05T05:17:43.162765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV","json":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV.json","graph_json":"https://pith.science/api/pith-number/J277QJRGY2RXWPXEEHY73DPEDV/graph.json","events_json":"https://pith.science/api/pith-number/J277QJRGY2RXWPXEEHY73DPEDV/events.json","paper":"https://pith.science/paper/J277QJRG"},"agent_actions":{"view_html":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV","download_json":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV.json","view_paper":"https://pith.science/paper/J277QJRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06607&json=true","fetch_graph":"https://pith.science/api/pith-number/J277QJRGY2RXWPXEEHY73DPEDV/graph.json","fetch_events":"https://pith.science/api/pith-number/J277QJRGY2RXWPXEEHY73DPEDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV/action/storage_attestation","attest_author":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV/action/author_attestation","sign_citation":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV/action/citation_signature","submit_replication":"https://pith.science/pith/J277QJRGY2RXWPXEEHY73DPEDV/action/replication_record"}},"created_at":"2026-07-05T05:17:43.162765+00:00","updated_at":"2026-07-05T05:17:43.162765+00:00"}