{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:USW4WCDXJFZBAFAF4H6TBLIKUN","short_pith_number":"pith:USW4WCDX","schema_version":"1.0","canonical_sha256":"a4adcb08774972101405e1fd30ad0aa37ca3e1954369c66e2a4bc7d660c9d103","source":{"kind":"arxiv","id":"2403.15082","version":3},"attestation_state":"computed","paper":{"title":"Cell Variational Information Bottleneck Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ju, Jinsong Lan, Shuai Xiao, Zhonghua Zhai","submitted_at":"2024-03-22T10:06:31Z","abstract_excerpt":"In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method. Our Cell Variational Information Bottleneck Network is constructed by stacking VIB cells, which generate feature maps with uncertainty. As layers going deeper, the regularization effect will gradually increase, instead of directly adding excessive regular constraints to the output layer of the model as in Deep VIB. Under each VIB cell, th"},"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":"2403.15082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T10:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"d1bcb8a4a9e57519f2a0405c5e27ad39f3950e9cf591456a6bc644c8dd6ce6de","abstract_canon_sha256":"d2eae703659d99b4918cde0ae4e4a44d24e590df695aa58dd504b2bfcbe85889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:06.062997Z","signature_b64":"VdZwRf4m4fbE8g6fASwBC9OhkPBIei+t+664GYxhTzoYn1QDIJF0cBUbCtMC1EcIIQ6N6pu1c+hflG4s/mDzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4adcb08774972101405e1fd30ad0aa37ca3e1954369c66e2a4bc7d660c9d103","last_reissued_at":"2026-07-05T08:02:06.062537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:06.062537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cell Variational Information Bottleneck Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ju, Jinsong Lan, Shuai Xiao, Zhonghua Zhai","submitted_at":"2024-03-22T10:06:31Z","abstract_excerpt":"In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method. Our Cell Variational Information Bottleneck Network is constructed by stacking VIB cells, which generate feature maps with uncertainty. As layers going deeper, the regularization effect will gradually increase, instead of directly adding excessive regular constraints to the output layer of the model as in Deep VIB. Under each VIB cell, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15082","kind":"arxiv","version":3},"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/2403.15082/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":"2403.15082","created_at":"2026-07-05T08:02:06.062606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15082v3","created_at":"2026-07-05T08:02:06.062606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15082","created_at":"2026-07-05T08:02:06.062606+00:00"},{"alias_kind":"pith_short_12","alias_value":"USW4WCDXJFZB","created_at":"2026-07-05T08:02:06.062606+00:00"},{"alias_kind":"pith_short_16","alias_value":"USW4WCDXJFZBAFAF","created_at":"2026-07-05T08:02:06.062606+00:00"},{"alias_kind":"pith_short_8","alias_value":"USW4WCDX","created_at":"2026-07-05T08:02:06.062606+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/USW4WCDXJFZBAFAF4H6TBLIKUN","json":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN.json","graph_json":"https://pith.science/api/pith-number/USW4WCDXJFZBAFAF4H6TBLIKUN/graph.json","events_json":"https://pith.science/api/pith-number/USW4WCDXJFZBAFAF4H6TBLIKUN/events.json","paper":"https://pith.science/paper/USW4WCDX"},"agent_actions":{"view_html":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN","download_json":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN.json","view_paper":"https://pith.science/paper/USW4WCDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15082&json=true","fetch_graph":"https://pith.science/api/pith-number/USW4WCDXJFZBAFAF4H6TBLIKUN/graph.json","fetch_events":"https://pith.science/api/pith-number/USW4WCDXJFZBAFAF4H6TBLIKUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN/action/storage_attestation","attest_author":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN/action/author_attestation","sign_citation":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN/action/citation_signature","submit_replication":"https://pith.science/pith/USW4WCDXJFZBAFAF4H6TBLIKUN/action/replication_record"}},"created_at":"2026-07-05T08:02:06.062606+00:00","updated_at":"2026-07-05T08:02:06.062606+00:00"}