{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZFXUBYEKPQDOCYMOZ74P6T4D32","short_pith_number":"pith:ZFXUBYEK","schema_version":"1.0","canonical_sha256":"c96f40e08a7c06e1618ecff8ff4f83dea5ad9711a02b036576d24a686cae2918","source":{"kind":"arxiv","id":"2304.09355","version":5},"attestation_state":"computed","paper":{"title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ravid Shwartz-Ziv, Yann LeCun","submitted_at":"2023-04-19T00:33:59Z","abstract_excerpt":"Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory, and notably the information bottleneck principle, has been pivotal in shaping deep neural networks. This principle focuses on optimizing the trade-off between compression and preserving relevant information, providing a foundation for efficient network design in supervised contexts. However, its precise role and adaptation in self-supervised learning "},"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":"2304.09355","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T00:33:59Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"ad13acdada78f7f9c7c46cd12f3c849e27cfa7dae7516d1a17e937c5ad12fb6a","abstract_canon_sha256":"680bcd13cce44a3caa2e1fc343ff9343cb516f89ee275de3e933740f031f9057"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:53.239489Z","signature_b64":"9RflNVThrzMCcfmSp0H48FVw57X/cVXhTXZoGU4kvOnu+caeYYpgjLD8JlNqpz8MIrNXiAwq5mshDu7OVZ+MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c96f40e08a7c06e1618ecff8ff4f83dea5ad9711a02b036576d24a686cae2918","last_reissued_at":"2026-07-05T07:14:53.238964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:53.238964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ravid Shwartz-Ziv, Yann LeCun","submitted_at":"2023-04-19T00:33:59Z","abstract_excerpt":"Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory, and notably the information bottleneck principle, has been pivotal in shaping deep neural networks. This principle focuses on optimizing the trade-off between compression and preserving relevant information, providing a foundation for efficient network design in supervised contexts. However, its precise role and adaptation in self-supervised learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09355","kind":"arxiv","version":5},"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/2304.09355/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":"2304.09355","created_at":"2026-07-05T07:14:53.239020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09355v5","created_at":"2026-07-05T07:14:53.239020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09355","created_at":"2026-07-05T07:14:53.239020+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFXUBYEKPQDO","created_at":"2026-07-05T07:14:53.239020+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFXUBYEKPQDOCYMO","created_at":"2026-07-05T07:14:53.239020+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFXUBYEK","created_at":"2026-07-05T07:14:53.239020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12809","citing_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32","json":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32.json","graph_json":"https://pith.science/api/pith-number/ZFXUBYEKPQDOCYMOZ74P6T4D32/graph.json","events_json":"https://pith.science/api/pith-number/ZFXUBYEKPQDOCYMOZ74P6T4D32/events.json","paper":"https://pith.science/paper/ZFXUBYEK"},"agent_actions":{"view_html":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32","download_json":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32.json","view_paper":"https://pith.science/paper/ZFXUBYEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09355&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFXUBYEKPQDOCYMOZ74P6T4D32/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFXUBYEKPQDOCYMOZ74P6T4D32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32/action/storage_attestation","attest_author":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32/action/author_attestation","sign_citation":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32/action/citation_signature","submit_replication":"https://pith.science/pith/ZFXUBYEKPQDOCYMOZ74P6T4D32/action/replication_record"}},"created_at":"2026-07-05T07:14:53.239020+00:00","updated_at":"2026-07-05T07:14:53.239020+00:00"}