{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WAYJNVESFSRI5KYDDUCG736MN2","short_pith_number":"pith:WAYJNVES","schema_version":"1.0","canonical_sha256":"b03096d4922ca28eab031d046fefcc6e896e89f2f5fec849eadbd3fe3955d3c0","source":{"kind":"arxiv","id":"2006.09286","version":3},"attestation_state":"computed","paper":{"title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arkil Patel, Navin Goyal, Satwik Bhattamishra","submitted_at":"2020-06-16T16:27:56Z","abstract_excerpt":"Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding of their power and inherent limitations is still nascent. In particular, the roles of various components in Transformers such as positional encodings, attention heads, residual connections, and feedforward networks, are not clear. In this paper, we take a step towards answering these questions. We analyze the computational power as captured by Turing-complete"},"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":"2006.09286","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T16:27:56Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"e7613d3587fdfd768eb0e3fd8af52e5b283010661864bfb4639a7e3a5c4c8f1f","abstract_canon_sha256":"519f5746d1cf983590b150d768e7bb22984dae49b822df6c739270808d32d466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:54.933835Z","signature_b64":"qfnJem4tYnjxPFLgL4n85UJffdhmREwnGlCSqCpYIXl9WaaXPd4qljEG5J4rtMJffGQjLdnP8ec+iYCSWbCNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b03096d4922ca28eab031d046fefcc6e896e89f2f5fec849eadbd3fe3955d3c0","last_reissued_at":"2026-07-05T01:41:54.933492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:54.933492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arkil Patel, Navin Goyal, Satwik Bhattamishra","submitted_at":"2020-06-16T16:27:56Z","abstract_excerpt":"Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding of their power and inherent limitations is still nascent. In particular, the roles of various components in Transformers such as positional encodings, attention heads, residual connections, and feedforward networks, are not clear. In this paper, we take a step towards answering these questions. We analyze the computational power as captured by Turing-complete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09286","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/2006.09286/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":"2006.09286","created_at":"2026-07-05T01:41:54.933543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09286v3","created_at":"2026-07-05T01:41:54.933543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09286","created_at":"2026-07-05T01:41:54.933543+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAYJNVESFSRI","created_at":"2026-07-05T01:41:54.933543+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAYJNVESFSRI5KYD","created_at":"2026-07-05T01:41:54.933543+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAYJNVES","created_at":"2026-07-05T01:41:54.933543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.16745","citing_title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02709","citing_title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2","json":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2.json","graph_json":"https://pith.science/api/pith-number/WAYJNVESFSRI5KYDDUCG736MN2/graph.json","events_json":"https://pith.science/api/pith-number/WAYJNVESFSRI5KYDDUCG736MN2/events.json","paper":"https://pith.science/paper/WAYJNVES"},"agent_actions":{"view_html":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2","download_json":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2.json","view_paper":"https://pith.science/paper/WAYJNVES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09286&json=true","fetch_graph":"https://pith.science/api/pith-number/WAYJNVESFSRI5KYDDUCG736MN2/graph.json","fetch_events":"https://pith.science/api/pith-number/WAYJNVESFSRI5KYDDUCG736MN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2/action/storage_attestation","attest_author":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2/action/author_attestation","sign_citation":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2/action/citation_signature","submit_replication":"https://pith.science/pith/WAYJNVESFSRI5KYDDUCG736MN2/action/replication_record"}},"created_at":"2026-07-05T01:41:54.933543+00:00","updated_at":"2026-07-05T01:41:54.933543+00:00"}