{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VSNJHS2KW3QM2NXM5OZ2BUNXPE","short_pith_number":"pith:VSNJHS2K","schema_version":"1.0","canonical_sha256":"ac9a93cb4ab6e0cd36ecebb3a0d1b779163055583533ec3eb7fa66b45f467893","source":{"kind":"arxiv","id":"1911.11423","version":2},"attestation_state":"computed","paper":{"title":"Single Headed Attention RNN: Stop Thinking With Your Head","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Stephen Merity","submitted_at":"2019-11-26T09:45:33Z","abstract_excerpt":"The leading approaches in language modeling are all obsessed with TV shows of my youth - namely Transformers and Sesame Street. Transformers this, Transformers that, and over here a bonfire worth of GPU-TPU-neuromorphic wafer scale silicon. We opt for the lazy path of old and proven techniques with a fancy crypto inspired acronym: the Single Headed Attention RNN (SHA-RNN). The author's lone goal is to show that the entire field might have evolved a different direction if we had instead been obsessed with a slightly different acronym and slightly different result. We take a previously strong la"},"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":"1911.11423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-26T09:45:33Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"5ace54217ec0849945264ad3b88a88f1712644ab8ffad55d61164f7969944d9f","abstract_canon_sha256":"5943c32d71d2c91ef67cfc15144b237737fddabeb28907e83584d9b0aa0ac326"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:27.100304Z","signature_b64":"ZqhJ5N9YYiugGPQnHL8zIjJ792UBGUnjR7njKmjzHK/PNIs5BuAWBhsFtegHNoK+O/FqSun2v2e9QfRKlsDABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9a93cb4ab6e0cd36ecebb3a0d1b779163055583533ec3eb7fa66b45f467893","last_reissued_at":"2026-07-05T00:22:27.099884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:27.099884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single Headed Attention RNN: Stop Thinking With Your Head","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Stephen Merity","submitted_at":"2019-11-26T09:45:33Z","abstract_excerpt":"The leading approaches in language modeling are all obsessed with TV shows of my youth - namely Transformers and Sesame Street. Transformers this, Transformers that, and over here a bonfire worth of GPU-TPU-neuromorphic wafer scale silicon. We opt for the lazy path of old and proven techniques with a fancy crypto inspired acronym: the Single Headed Attention RNN (SHA-RNN). The author's lone goal is to show that the entire field might have evolved a different direction if we had instead been obsessed with a slightly different acronym and slightly different result. We take a previously strong la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11423","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/1911.11423/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":"1911.11423","created_at":"2026-07-05T00:22:27.099947+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11423v2","created_at":"2026-07-05T00:22:27.099947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11423","created_at":"2026-07-05T00:22:27.099947+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSNJHS2KW3QM","created_at":"2026-07-05T00:22:27.099947+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSNJHS2KW3QM2NXM","created_at":"2026-07-05T00:22:27.099947+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSNJHS2K","created_at":"2026-07-05T00:22:27.099947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00617","citing_title":"Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE","json":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE.json","graph_json":"https://pith.science/api/pith-number/VSNJHS2KW3QM2NXM5OZ2BUNXPE/graph.json","events_json":"https://pith.science/api/pith-number/VSNJHS2KW3QM2NXM5OZ2BUNXPE/events.json","paper":"https://pith.science/paper/VSNJHS2K"},"agent_actions":{"view_html":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE","download_json":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE.json","view_paper":"https://pith.science/paper/VSNJHS2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11423&json=true","fetch_graph":"https://pith.science/api/pith-number/VSNJHS2KW3QM2NXM5OZ2BUNXPE/graph.json","fetch_events":"https://pith.science/api/pith-number/VSNJHS2KW3QM2NXM5OZ2BUNXPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE/action/storage_attestation","attest_author":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE/action/author_attestation","sign_citation":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE/action/citation_signature","submit_replication":"https://pith.science/pith/VSNJHS2KW3QM2NXM5OZ2BUNXPE/action/replication_record"}},"created_at":"2026-07-05T00:22:27.099947+00:00","updated_at":"2026-07-05T00:22:27.099947+00:00"}