{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PA2UMU32EGZWV55A4MBWTBSOZX","short_pith_number":"pith:PA2UMU32","schema_version":"1.0","canonical_sha256":"783546537a21b36af7a0e30369864ecdd054cf0fc40849d43ab5b323d6e2d710","source":{"kind":"arxiv","id":"2509.01804","version":1},"attestation_state":"computed","paper":{"title":"Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CV","authors_text":"Jun Cheng, Shan Tan, Xin Cai, Yifan Lan","submitted_at":"2025-09-01T22:14:12Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and deployment of DNNs. Information bottleneck (IB) is an elegant approach for representation learning. In this paper, we propose a balanced information bottleneck (BIB) approach, in which loss function re-balancing and self-distillation techniques are integrated into the original IB network. BIB is thus capable of learning a sufficient representation with essen"},"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":"2509.01804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T22:14:12Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"77a7e3ec4f7b7d2a9acc2d732d37ceb3a62538493e29c9d79cdfdd6cc6bae4f2","abstract_canon_sha256":"ff0afdaf7b66aa026b70735479d9ccbfb045b8188aba3c868c3cf145f425d2f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:09.189805Z","signature_b64":"WHzEkAUtcmAOh+g8NeZevh8+Qf+T/zJz6PKWZTTtx0Q49IIIb93nP5htY/W0LeJMe2yno/vgPnGBGOGm10WABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"783546537a21b36af7a0e30369864ecdd054cf0fc40849d43ab5b323d6e2d710","last_reissued_at":"2026-07-05T12:03:09.189234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:09.189234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CV","authors_text":"Jun Cheng, Shan Tan, Xin Cai, Yifan Lan","submitted_at":"2025-09-01T22:14:12Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and deployment of DNNs. Information bottleneck (IB) is an elegant approach for representation learning. In this paper, we propose a balanced information bottleneck (BIB) approach, in which loss function re-balancing and self-distillation techniques are integrated into the original IB network. BIB is thus capable of learning a sufficient representation with essen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01804","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/2509.01804/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":"2509.01804","created_at":"2026-07-05T12:03:09.189294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01804v1","created_at":"2026-07-05T12:03:09.189294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01804","created_at":"2026-07-05T12:03:09.189294+00:00"},{"alias_kind":"pith_short_12","alias_value":"PA2UMU32EGZW","created_at":"2026-07-05T12:03:09.189294+00:00"},{"alias_kind":"pith_short_16","alias_value":"PA2UMU32EGZWV55A","created_at":"2026-07-05T12:03:09.189294+00:00"},{"alias_kind":"pith_short_8","alias_value":"PA2UMU32","created_at":"2026-07-05T12:03:09.189294+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/PA2UMU32EGZWV55A4MBWTBSOZX","json":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX.json","graph_json":"https://pith.science/api/pith-number/PA2UMU32EGZWV55A4MBWTBSOZX/graph.json","events_json":"https://pith.science/api/pith-number/PA2UMU32EGZWV55A4MBWTBSOZX/events.json","paper":"https://pith.science/paper/PA2UMU32"},"agent_actions":{"view_html":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX","download_json":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX.json","view_paper":"https://pith.science/paper/PA2UMU32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01804&json=true","fetch_graph":"https://pith.science/api/pith-number/PA2UMU32EGZWV55A4MBWTBSOZX/graph.json","fetch_events":"https://pith.science/api/pith-number/PA2UMU32EGZWV55A4MBWTBSOZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX/action/storage_attestation","attest_author":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX/action/author_attestation","sign_citation":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX/action/citation_signature","submit_replication":"https://pith.science/pith/PA2UMU32EGZWV55A4MBWTBSOZX/action/replication_record"}},"created_at":"2026-07-05T12:03:09.189294+00:00","updated_at":"2026-07-05T12:03:09.189294+00:00"}