{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FT2P63EG3FT5326X6R2YBDKWG2","short_pith_number":"pith:FT2P63EG","schema_version":"1.0","canonical_sha256":"2cf4ff6c86d967ddebd7f475808d563698d9c6d546c043abcccf98b8354e61d7","source":{"kind":"arxiv","id":"2103.12300","version":1},"attestation_state":"computed","paper":{"title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyeon Woo, Gunhee Kim, Jaekyeom Kim, Minjung Kim","submitted_at":"2021-03-23T04:31:28Z","abstract_excerpt":"We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also additionally provides a deterministic compressed representation of the input variable, which is useful for inference tasks that require consistent representation. Moreover, it can jointly learn a feature extractor and select features considering each feature dimension's relevance to the target task, which is unattainable by most neural network-based IB method"},"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":"2103.12300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T04:31:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c273890ca9ecded6fe419affaf65eacabf71e3e4ee50e88836baacfb822574c","abstract_canon_sha256":"4dbad0237967dbec6bbbe386f0a8726b35d172e5ad811f4ed7841f0cc2c1bded"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:44.961458Z","signature_b64":"ilXRiJQnLz/chWuGK3G934uFgDo4bsxtXzZpomF0+IC8x2Rx6NZk73OptEPGVDI37RRwwyzYLH13mEIIM5AnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf4ff6c86d967ddebd7f475808d563698d9c6d546c043abcccf98b8354e61d7","last_reissued_at":"2026-07-05T02:25:44.961066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:44.961066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyeon Woo, Gunhee Kim, Jaekyeom Kim, Minjung Kim","submitted_at":"2021-03-23T04:31:28Z","abstract_excerpt":"We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also additionally provides a deterministic compressed representation of the input variable, which is useful for inference tasks that require consistent representation. Moreover, it can jointly learn a feature extractor and select features considering each feature dimension's relevance to the target task, which is unattainable by most neural network-based IB method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12300","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/2103.12300/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":"2103.12300","created_at":"2026-07-05T02:25:44.961120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12300v1","created_at":"2026-07-05T02:25:44.961120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12300","created_at":"2026-07-05T02:25:44.961120+00:00"},{"alias_kind":"pith_short_12","alias_value":"FT2P63EG3FT5","created_at":"2026-07-05T02:25:44.961120+00:00"},{"alias_kind":"pith_short_16","alias_value":"FT2P63EG3FT5326X","created_at":"2026-07-05T02:25:44.961120+00:00"},{"alias_kind":"pith_short_8","alias_value":"FT2P63EG","created_at":"2026-07-05T02:25:44.961120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01804","citing_title":"Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2","json":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2.json","graph_json":"https://pith.science/api/pith-number/FT2P63EG3FT5326X6R2YBDKWG2/graph.json","events_json":"https://pith.science/api/pith-number/FT2P63EG3FT5326X6R2YBDKWG2/events.json","paper":"https://pith.science/paper/FT2P63EG"},"agent_actions":{"view_html":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2","download_json":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2.json","view_paper":"https://pith.science/paper/FT2P63EG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12300&json=true","fetch_graph":"https://pith.science/api/pith-number/FT2P63EG3FT5326X6R2YBDKWG2/graph.json","fetch_events":"https://pith.science/api/pith-number/FT2P63EG3FT5326X6R2YBDKWG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2/action/storage_attestation","attest_author":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2/action/author_attestation","sign_citation":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2/action/citation_signature","submit_replication":"https://pith.science/pith/FT2P63EG3FT5326X6R2YBDKWG2/action/replication_record"}},"created_at":"2026-07-05T02:25:44.961120+00:00","updated_at":"2026-07-05T02:25:44.961120+00:00"}