{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FXWWARFMGVIFYGMCEBV7DOYM3S","short_pith_number":"pith:FXWWARFM","schema_version":"1.0","canonical_sha256":"2ded6044ac35505c1982206bf1bb0cdc86ac281f6b0f7b8d8076faecb860fe49","source":{"kind":"arxiv","id":"2402.01238","version":1},"attestation_state":"computed","paper":{"title":"Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ming Huang, Naoaki Ono, Shigehiko Kanaya, Sota Kudo","submitted_at":"2024-02-02T09:03:38Z","abstract_excerpt":"Information Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off between data compression and predictiveness through the Lagrange multiplier $\\beta$. Traditionally, to find the trade-off to be learned, IB requires a search for $\\beta$ through multiple training cycles, which is computationally expensive. In this study, we introduce Flexible Variational Information Bottleneck (FVIB), an innovative framework for classification task that can obtai"},"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":"2402.01238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T09:03:38Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"14832523747f9566b048ac2ba945043848bc081191dccd9b996af8871fbfed01","abstract_canon_sha256":"6f587ca10095970cc5f2b8fd994f0bfca4e59cccc6a8ebef35a3d7931134fabf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:45.994652Z","signature_b64":"xrLaC53aVXAHA+n+71lLCChKCIWZiK/w0o8y0OWOIuP5tVH3EO83wduZS9vsZ22itz1NRy272ZfTjhnUiuPYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ded6044ac35505c1982206bf1bb0cdc86ac281f6b0f7b8d8076faecb860fe49","last_reissued_at":"2026-07-05T11:52:45.994179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:45.994179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ming Huang, Naoaki Ono, Shigehiko Kanaya, Sota Kudo","submitted_at":"2024-02-02T09:03:38Z","abstract_excerpt":"Information Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off between data compression and predictiveness through the Lagrange multiplier $\\beta$. Traditionally, to find the trade-off to be learned, IB requires a search for $\\beta$ through multiple training cycles, which is computationally expensive. In this study, we introduce Flexible Variational Information Bottleneck (FVIB), an innovative framework for classification task that can obtai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01238","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/2402.01238/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":"2402.01238","created_at":"2026-07-05T11:52:45.994236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01238v1","created_at":"2026-07-05T11:52:45.994236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01238","created_at":"2026-07-05T11:52:45.994236+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXWWARFMGVIF","created_at":"2026-07-05T11:52:45.994236+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXWWARFMGVIFYGMC","created_at":"2026-07-05T11:52:45.994236+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXWWARFM","created_at":"2026-07-05T11:52:45.994236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14077","citing_title":"Label Smoothing is a Pragmatic Information Bottleneck","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S","json":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S.json","graph_json":"https://pith.science/api/pith-number/FXWWARFMGVIFYGMCEBV7DOYM3S/graph.json","events_json":"https://pith.science/api/pith-number/FXWWARFMGVIFYGMCEBV7DOYM3S/events.json","paper":"https://pith.science/paper/FXWWARFM"},"agent_actions":{"view_html":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S","download_json":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S.json","view_paper":"https://pith.science/paper/FXWWARFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01238&json=true","fetch_graph":"https://pith.science/api/pith-number/FXWWARFMGVIFYGMCEBV7DOYM3S/graph.json","fetch_events":"https://pith.science/api/pith-number/FXWWARFMGVIFYGMCEBV7DOYM3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S/action/storage_attestation","attest_author":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S/action/author_attestation","sign_citation":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S/action/citation_signature","submit_replication":"https://pith.science/pith/FXWWARFMGVIFYGMCEBV7DOYM3S/action/replication_record"}},"created_at":"2026-07-05T11:52:45.994236+00:00","updated_at":"2026-07-05T11:52:45.994236+00:00"}