{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3RXTPOIQMDC2KU57YHYHFWJHW","short_pith_number":"pith:Z3RXTPOI","schema_version":"1.0","canonical_sha256":"cee379bdc883062d2a9dfe0f8396c93da4f75841e621fa32cae38f32f350e311","source":{"kind":"arxiv","id":"2411.07602","version":2},"attestation_state":"computed","paper":{"title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Chen, Jiangxuan Long, Xiaoyu Li, Yingyu Liang, Zhao Song, Zhenmei Shi","submitted_at":"2024-11-12T07:24:41Z","abstract_excerpt":"Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand, Rotary Position Embedding ($\\mathsf{RoPE}$) has emerged as a crucial technique in modern large language models, offering superior performance in capturing positional information compared to traditional position embeddings, which shows great potential in application prospects, particularly for the long context scenario. Empirical evidence also suggests that $\\math"},"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":"2411.07602","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T07:24:41Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CL"],"title_canon_sha256":"aa918a58b42d05f5570f32073de63c396b94227833659e1b67e957e6dfb7f5fb","abstract_canon_sha256":"68d0a3a28f524f6bad66e2121698c58873bf4e9e81dc8a03f5ffb13d053c6f4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:32.384556Z","signature_b64":"mpCoORmKcn1Ji/gtXh5EjOFFtuD4Vn6XP2T4lTD0C9TxMi2rw1v30++RcHN+tgiM7X7kpzVxLAPv+pFnPoMCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cee379bdc883062d2a9dfe0f8396c93da4f75841e621fa32cae38f32f350e311","last_reissued_at":"2026-07-05T09:42:32.384041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:32.384041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Chen, Jiangxuan Long, Xiaoyu Li, Yingyu Liang, Zhao Song, Zhenmei Shi","submitted_at":"2024-11-12T07:24:41Z","abstract_excerpt":"Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand, Rotary Position Embedding ($\\mathsf{RoPE}$) has emerged as a crucial technique in modern large language models, offering superior performance in capturing positional information compared to traditional position embeddings, which shows great potential in application prospects, particularly for the long context scenario. Empirical evidence also suggests that $\\math"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07602","kind":"arxiv","version":2},"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/2411.07602/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":"2411.07602","created_at":"2026-07-05T09:42:32.384109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07602v2","created_at":"2026-07-05T09:42:32.384109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07602","created_at":"2026-07-05T09:42:32.384109+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3RXTPOIQMDC","created_at":"2026-07-05T09:42:32.384109+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3RXTPOIQMDC2KU5","created_at":"2026-07-05T09:42:32.384109+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3RXTPOI","created_at":"2026-07-05T09:42:32.384109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19531","citing_title":"Minimalist Softmax Attention Provably Learns Constrained Boolean Functions","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW","json":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW.json","graph_json":"https://pith.science/api/pith-number/Z3RXTPOIQMDC2KU57YHYHFWJHW/graph.json","events_json":"https://pith.science/api/pith-number/Z3RXTPOIQMDC2KU57YHYHFWJHW/events.json","paper":"https://pith.science/paper/Z3RXTPOI"},"agent_actions":{"view_html":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW","download_json":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW.json","view_paper":"https://pith.science/paper/Z3RXTPOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07602&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3RXTPOIQMDC2KU57YHYHFWJHW/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3RXTPOIQMDC2KU57YHYHFWJHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW/action/storage_attestation","attest_author":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW/action/author_attestation","sign_citation":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW/action/citation_signature","submit_replication":"https://pith.science/pith/Z3RXTPOIQMDC2KU57YHYHFWJHW/action/replication_record"}},"created_at":"2026-07-05T09:42:32.384109+00:00","updated_at":"2026-07-05T09:42:32.384109+00:00"}