{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YGJ3GC43NODL4KL6IXBJHG662C","short_pith_number":"pith:YGJ3GC43","schema_version":"1.0","canonical_sha256":"c193b30b9b6b86be297e45c2939bded0853a4fd734ee2853a1db6c1d553ab2fd","source":{"kind":"arxiv","id":"2410.01600","version":3},"attestation_state":"computed","paper":{"title":"ENTP: Encoder-only Next Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daewon Chae, Ethan Ewer, Jinkyu Kim, Kangwook Lee, Thomas Zeng","submitted_at":"2024-10-02T14:39:13Z","abstract_excerpt":"Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not compute-limited, should we still use decoder-only Transformers? In this work, we introduce Encoder-only Next Token Prediction (ENTP). We explore the differences between ENTP and decoder-only Transformers in expressive power and complexity, highlighting potential advantages of ENTP in settings with unbounded compute. We introduce the $\\operatorname{Count3}$ task and show, both theoretically and experimentally, tha"},"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":"2410.01600","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T14:39:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7a24de63f65a03844a83cf977696d5ec1fcc00ab5603b84e935523b832a4ee58","abstract_canon_sha256":"a1f0d0a48935c53b4f83ce57bfab098a60f2bc6159c5b8562d02c9493b5cb744"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:09.703791Z","signature_b64":"QvxKor4oBYWuKfeNVYmyKbs37o+0C/MT2TJBB+wwwNiWTXwRpu9nYLoioEtJ10rUgSdam+06bEwJhOhqOMHOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c193b30b9b6b86be297e45c2939bded0853a4fd734ee2853a1db6c1d553ab2fd","last_reissued_at":"2026-07-05T10:09:09.703250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:09.703250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ENTP: Encoder-only Next Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daewon Chae, Ethan Ewer, Jinkyu Kim, Kangwook Lee, Thomas Zeng","submitted_at":"2024-10-02T14:39:13Z","abstract_excerpt":"Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not compute-limited, should we still use decoder-only Transformers? In this work, we introduce Encoder-only Next Token Prediction (ENTP). We explore the differences between ENTP and decoder-only Transformers in expressive power and complexity, highlighting potential advantages of ENTP in settings with unbounded compute. We introduce the $\\operatorname{Count3}$ task and show, both theoretically and experimentally, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01600","kind":"arxiv","version":3},"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/2410.01600/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":"2410.01600","created_at":"2026-07-05T10:09:09.703344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01600v3","created_at":"2026-07-05T10:09:09.703344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01600","created_at":"2026-07-05T10:09:09.703344+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGJ3GC43NODL","created_at":"2026-07-05T10:09:09.703344+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGJ3GC43NODL4KL6","created_at":"2026-07-05T10:09:09.703344+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGJ3GC43","created_at":"2026-07-05T10:09:09.703344+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/YGJ3GC43NODL4KL6IXBJHG662C","json":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C.json","graph_json":"https://pith.science/api/pith-number/YGJ3GC43NODL4KL6IXBJHG662C/graph.json","events_json":"https://pith.science/api/pith-number/YGJ3GC43NODL4KL6IXBJHG662C/events.json","paper":"https://pith.science/paper/YGJ3GC43"},"agent_actions":{"view_html":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C","download_json":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C.json","view_paper":"https://pith.science/paper/YGJ3GC43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01600&json=true","fetch_graph":"https://pith.science/api/pith-number/YGJ3GC43NODL4KL6IXBJHG662C/graph.json","fetch_events":"https://pith.science/api/pith-number/YGJ3GC43NODL4KL6IXBJHG662C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C/action/storage_attestation","attest_author":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C/action/author_attestation","sign_citation":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C/action/citation_signature","submit_replication":"https://pith.science/pith/YGJ3GC43NODL4KL6IXBJHG662C/action/replication_record"}},"created_at":"2026-07-05T10:09:09.703344+00:00","updated_at":"2026-07-05T10:09:09.703344+00:00"}