{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HKLEPQWCSEEIRT236SCT2BZ3JA","short_pith_number":"pith:HKLEPQWC","schema_version":"1.0","canonical_sha256":"3a9647c2c2910888cf5bf4853d073b480c23c78330d548f2ae29ddd58dbad230","source":{"kind":"arxiv","id":"2002.07017","version":2},"attestation_state":"computed","paper":{"title":"Learning Robust Representations via Multi-View Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjan Dutta, Marco Federici, Nate Kushman, Patrick Forr\\'e, Zeynep Akata","submitted_at":"2020-02-17T16:01:52Z","abstract_excerpt":"The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess information in the representation. The original formulation, however, requires labeled data to identify the superfluous information. In this work, we extend this ability to the multi-view unsupervised setting, where two views of the same underlying entity are provided but the label is unknown. This enables us to identify superfluous information as that n"},"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":"2002.07017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T16:01:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6207a8cfb18ccb27d225c8d1317c841d6c4049dbcda88e43ccba7e9d94b9861d","abstract_canon_sha256":"f298a6c8a0ff8ecc67abff505bb500ecb331d4e5ca12a0a4868a18df4b91047d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:01.368688Z","signature_b64":"LuQ8zYvyPy4tr/7518e39NtcRdtGyG51dL+b+cfBfwLn8S0bZ8Xicas2AYpEGdfMG397ZW9slC8wasommFOXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9647c2c2910888cf5bf4853d073b480c23c78330d548f2ae29ddd58dbad230","last_reissued_at":"2026-07-05T00:42:01.367829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:01.367829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Robust Representations via Multi-View Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjan Dutta, Marco Federici, Nate Kushman, Patrick Forr\\'e, Zeynep Akata","submitted_at":"2020-02-17T16:01:52Z","abstract_excerpt":"The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess information in the representation. The original formulation, however, requires labeled data to identify the superfluous information. In this work, we extend this ability to the multi-view unsupervised setting, where two views of the same underlying entity are provided but the label is unknown. This enables us to identify superfluous information as that n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07017","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/2002.07017/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":"2002.07017","created_at":"2026-07-05T00:42:01.367923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07017v2","created_at":"2026-07-05T00:42:01.367923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07017","created_at":"2026-07-05T00:42:01.367923+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKLEPQWCSEEI","created_at":"2026-07-05T00:42:01.367923+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKLEPQWCSEEIRT23","created_at":"2026-07-05T00:42:01.367923+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKLEPQWC","created_at":"2026-07-05T00:42:01.367923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11614","citing_title":"Information-Theoretic Decomposition for Multimodal Interaction Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01821","citing_title":"Pattern-Calibrated Multimodal Prediction under Blockwise Missingness","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03463","citing_title":"Super Agents and Confounders: Influence of surrounding agents on vehicle trajectory prediction","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18460","citing_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA","json":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA.json","graph_json":"https://pith.science/api/pith-number/HKLEPQWCSEEIRT236SCT2BZ3JA/graph.json","events_json":"https://pith.science/api/pith-number/HKLEPQWCSEEIRT236SCT2BZ3JA/events.json","paper":"https://pith.science/paper/HKLEPQWC"},"agent_actions":{"view_html":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA","download_json":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA.json","view_paper":"https://pith.science/paper/HKLEPQWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07017&json=true","fetch_graph":"https://pith.science/api/pith-number/HKLEPQWCSEEIRT236SCT2BZ3JA/graph.json","fetch_events":"https://pith.science/api/pith-number/HKLEPQWCSEEIRT236SCT2BZ3JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA/action/storage_attestation","attest_author":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA/action/author_attestation","sign_citation":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA/action/citation_signature","submit_replication":"https://pith.science/pith/HKLEPQWCSEEIRT236SCT2BZ3JA/action/replication_record"}},"created_at":"2026-07-05T00:42:01.367923+00:00","updated_at":"2026-07-05T00:42:01.367923+00:00"}