{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W7OIS7IEVGJVGJ4ZPRDKLMRHMP","short_pith_number":"pith:W7OIS7IE","schema_version":"1.0","canonical_sha256":"b7dc897d04a9935327997c46a5b22763c36b8decdf0b6306366ff0d6cdba16ac","source":{"kind":"arxiv","id":"2411.17182","version":1},"attestation_state":"computed","paper":{"title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Difan Zou, Dong Xu, Yunzhe Hu","submitted_at":"2024-11-26T07:44:57Z","abstract_excerpt":"Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \\cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive differ"},"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":"2411.17182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T07:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"0737d513f8a11dae8f12cfff631c5b10c89a4eb4e76204b629f7f313aa4843fe","abstract_canon_sha256":"4e0afa147233bb1d75d7d47eb1442e4257bb3e756b0e0ba9d74b8eb2b2529bf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:28.811997Z","signature_b64":"JTl8VcjNC5lmxR9WD31u9ySyzLPZYPPjpNTjzE7zsp9znjJCdVMt1QrQsdlOph9JO/OM7L76hcT+lE1Yev6KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7dc897d04a9935327997c46a5b22763c36b8decdf0b6306366ff0d6cdba16ac","last_reissued_at":"2026-07-05T09:40:28.811563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:28.811563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Difan Zou, Dong Xu, Yunzhe Hu","submitted_at":"2024-11-26T07:44:57Z","abstract_excerpt":"Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \\cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17182","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/2411.17182/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":"2411.17182","created_at":"2026-07-05T09:40:28.811619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17182v1","created_at":"2026-07-05T09:40:28.811619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17182","created_at":"2026-07-05T09:40:28.811619+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7OIS7IEVGJV","created_at":"2026-07-05T09:40:28.811619+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7OIS7IEVGJVGJ4Z","created_at":"2026-07-05T09:40:28.811619+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7OIS7IE","created_at":"2026-07-05T09:40:28.811619+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/W7OIS7IEVGJVGJ4ZPRDKLMRHMP","json":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP.json","graph_json":"https://pith.science/api/pith-number/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/graph.json","events_json":"https://pith.science/api/pith-number/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/events.json","paper":"https://pith.science/paper/W7OIS7IE"},"agent_actions":{"view_html":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP","download_json":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP.json","view_paper":"https://pith.science/paper/W7OIS7IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17182&json=true","fetch_graph":"https://pith.science/api/pith-number/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/graph.json","fetch_events":"https://pith.science/api/pith-number/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/action/storage_attestation","attest_author":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/action/author_attestation","sign_citation":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/action/citation_signature","submit_replication":"https://pith.science/pith/W7OIS7IEVGJVGJ4ZPRDKLMRHMP/action/replication_record"}},"created_at":"2026-07-05T09:40:28.811619+00:00","updated_at":"2026-07-05T09:40:28.811619+00:00"}