{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2JSFPNQYFWDVLMTBELRQTUCYTK","short_pith_number":"pith:2JSFPNQY","schema_version":"1.0","canonical_sha256":"d26457b6182d8755b26122e309d0589aae613631a2aa539fed77c90e563a1798","source":{"kind":"arxiv","id":"2312.12742","version":1},"attestation_state":"computed","paper":{"title":"Cached Transformers: Improving Transformers with Differentiable Memory Cache","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinwei Gu, Ping Luo, Wenqi Shao, Xiaogang Wang, Yixiao Ge, Zhaoyang Zhang","submitted_at":"2023-12-20T03:30:51Z","abstract_excerpt":"This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \\textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classific"},"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":"2312.12742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T03:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"2bec9a719759216382deb2292bebc8e4f8c16c2d38a546dbc2b22198c00215f1","abstract_canon_sha256":"b02311e510bee6a98cb857b2a578014bc96fc7d92e2fd5c3e7b2a120324f7cc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:25.824501Z","signature_b64":"ZIIH4kv/mLDS8VOt1xgneQXA96TIuFsGEJP9v2n0Wh9VyUtCyGEzHvxykz+vRMxKBzsSdxjsKu/WZVC/MKbQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d26457b6182d8755b26122e309d0589aae613631a2aa539fed77c90e563a1798","last_reissued_at":"2026-07-05T07:26:25.824045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:25.824045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cached Transformers: Improving Transformers with Differentiable Memory Cache","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinwei Gu, Ping Luo, Wenqi Shao, Xiaogang Wang, Yixiao Ge, Zhaoyang Zhang","submitted_at":"2023-12-20T03:30:51Z","abstract_excerpt":"This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \\textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12742","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/2312.12742/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":"2312.12742","created_at":"2026-07-05T07:26:25.824103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12742v1","created_at":"2026-07-05T07:26:25.824103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12742","created_at":"2026-07-05T07:26:25.824103+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JSFPNQYFWDV","created_at":"2026-07-05T07:26:25.824103+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JSFPNQYFWDVLMTB","created_at":"2026-07-05T07:26:25.824103+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JSFPNQY","created_at":"2026-07-05T07:26:25.824103+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/2JSFPNQYFWDVLMTBELRQTUCYTK","json":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK.json","graph_json":"https://pith.science/api/pith-number/2JSFPNQYFWDVLMTBELRQTUCYTK/graph.json","events_json":"https://pith.science/api/pith-number/2JSFPNQYFWDVLMTBELRQTUCYTK/events.json","paper":"https://pith.science/paper/2JSFPNQY"},"agent_actions":{"view_html":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK","download_json":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK.json","view_paper":"https://pith.science/paper/2JSFPNQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12742&json=true","fetch_graph":"https://pith.science/api/pith-number/2JSFPNQYFWDVLMTBELRQTUCYTK/graph.json","fetch_events":"https://pith.science/api/pith-number/2JSFPNQYFWDVLMTBELRQTUCYTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK/action/storage_attestation","attest_author":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK/action/author_attestation","sign_citation":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK/action/citation_signature","submit_replication":"https://pith.science/pith/2JSFPNQYFWDVLMTBELRQTUCYTK/action/replication_record"}},"created_at":"2026-07-05T07:26:25.824103+00:00","updated_at":"2026-07-05T07:26:25.824103+00:00"}