{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LVTYHF3R2QQMJ74JIIJWUS4D5B","short_pith_number":"pith:LVTYHF3R","schema_version":"1.0","canonical_sha256":"5d67839771d420c4ff8942136a4b83e86be17858082c51a71da1eed39c2bf031","source":{"kind":"arxiv","id":"2305.11213","version":1},"attestation_state":"computed","paper":{"title":"Information-Ordered Bottlenecks for Adaptive Semantic Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Wandelt, Matthew Ho, Xiaosheng Zhao","submitted_at":"2023-05-18T18:00:00Z","abstract_excerpt":"We present the information-ordered bottleneck (IOB), a neural layer designed to adaptively compress data into latent variables ordered by likelihood maximization. Without retraining, IOB nodes can be truncated at any bottleneck width, capturing the most crucial information in the first latent variables. Unifying several previous approaches, we show that IOBs achieve near-optimal compression for a given encoding architecture and can assign ordering to latent signals in a manner that is semantically meaningful. IOBs demonstrate a remarkable ability to compress embeddings of image and text data, "},"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":"2305.11213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T18:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"414ad6894cbfcef046b39964144d9e9fb6c037cd02a11ceecd39918a322f4a6a","abstract_canon_sha256":"7cc8b8825b73ec623c87a46ea0075ff3b6519045f97b8a3dbc0287d44bea9a3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:34.362195Z","signature_b64":"7dsucLh5RZn9u9VSgoj9kPjhFFwdcOFnjbpEogZ+w1ubkK0/cevqnxeOG157ig+0knP0uCb0Lw/gBhnuOezlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d67839771d420c4ff8942136a4b83e86be17858082c51a71da1eed39c2bf031","last_reissued_at":"2026-07-05T06:11:34.361756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:34.361756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-Ordered Bottlenecks for Adaptive Semantic Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Wandelt, Matthew Ho, Xiaosheng Zhao","submitted_at":"2023-05-18T18:00:00Z","abstract_excerpt":"We present the information-ordered bottleneck (IOB), a neural layer designed to adaptively compress data into latent variables ordered by likelihood maximization. Without retraining, IOB nodes can be truncated at any bottleneck width, capturing the most crucial information in the first latent variables. Unifying several previous approaches, we show that IOBs achieve near-optimal compression for a given encoding architecture and can assign ordering to latent signals in a manner that is semantically meaningful. IOBs demonstrate a remarkable ability to compress embeddings of image and text data, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11213","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/2305.11213/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":"2305.11213","created_at":"2026-07-05T06:11:34.361809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11213v1","created_at":"2026-07-05T06:11:34.361809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11213","created_at":"2026-07-05T06:11:34.361809+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVTYHF3R2QQM","created_at":"2026-07-05T06:11:34.361809+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVTYHF3R2QQMJ74J","created_at":"2026-07-05T06:11:34.361809+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVTYHF3R","created_at":"2026-07-05T06:11:34.361809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10027","citing_title":"Learning the Universe: The Structure of Dust Attenuation Curves in Galaxy Simulations","ref_index":239,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B","json":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B.json","graph_json":"https://pith.science/api/pith-number/LVTYHF3R2QQMJ74JIIJWUS4D5B/graph.json","events_json":"https://pith.science/api/pith-number/LVTYHF3R2QQMJ74JIIJWUS4D5B/events.json","paper":"https://pith.science/paper/LVTYHF3R"},"agent_actions":{"view_html":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B","download_json":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B.json","view_paper":"https://pith.science/paper/LVTYHF3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11213&json=true","fetch_graph":"https://pith.science/api/pith-number/LVTYHF3R2QQMJ74JIIJWUS4D5B/graph.json","fetch_events":"https://pith.science/api/pith-number/LVTYHF3R2QQMJ74JIIJWUS4D5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B/action/storage_attestation","attest_author":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B/action/author_attestation","sign_citation":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B/action/citation_signature","submit_replication":"https://pith.science/pith/LVTYHF3R2QQMJ74JIIJWUS4D5B/action/replication_record"}},"created_at":"2026-07-05T06:11:34.361809+00:00","updated_at":"2026-07-05T06:11:34.361809+00:00"}