{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JWDWNIKRCBW4K7TJ6USVAFXSLK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bde746d60748c737949c0d51d23d558dcb511cdccde2e01e7c91387d90a64f27","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T19:39:15Z","title_canon_sha256":"6cd30be592aaf2ba2dcc53f94a2e2f64b38306293b1bcef835bebfae8179ff72"},"schema_version":"1.0","source":{"id":"2009.04534","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04534","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04534v3","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04534","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"JWDWNIKRCBW4","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_16","alias_value":"JWDWNIKRCBW4K7TJ","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_8","alias_value":"JWDWNIKR","created_at":"2026-07-05T02:40:28Z"}],"graph_snapshots":[{"event_id":"sha256:2e31c7ea1dc7f1b557191dc227f7c50359349672eae93255631f019c1c76ece9","target":"graph","created_at":"2026-07-05T02:40:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.04534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of the blocks to improve upon the current Transformer architecture and proposed PAR Transformer. It needs 35% lower compute time than Transformer-XL achieved by replacing ~63% of the self-attention blocks with feed-forward blocks, and retains the perplexity on WikiText-103 language modelling benchmark. We further validated our results on text8 and enwiki8 dataset","authors_text":"Alex Fit Florea, Swetha Mandava, Szymon Migacz","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T19:39:15Z","title":"Pay Attention when Required"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04534","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8783dab4a20c017aef0642a63464889c69d3b56f994cb49057b5096eb43c219e","target":"record","created_at":"2026-07-05T02:40:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bde746d60748c737949c0d51d23d558dcb511cdccde2e01e7c91387d90a64f27","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T19:39:15Z","title_canon_sha256":"6cd30be592aaf2ba2dcc53f94a2e2f64b38306293b1bcef835bebfae8179ff72"},"schema_version":"1.0","source":{"id":"2009.04534","kind":"arxiv","version":3}},"canonical_sha256":"4d8766a151106dc57e69f5255016f25aa83a0788e26f833a165d6dbebd149fd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d8766a151106dc57e69f5255016f25aa83a0788e26f833a165d6dbebd149fd1","first_computed_at":"2026-07-05T02:40:28.724102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:28.724102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2EIBWxcGSq1krI99vTPbWQp0XY9plSsWMntW7k9ZCHtuHVBpyephjGMtAvogF1HNO88wRplwTf506d1jagNJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:28.724704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.04534","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8783dab4a20c017aef0642a63464889c69d3b56f994cb49057b5096eb43c219e","sha256:2e31c7ea1dc7f1b557191dc227f7c50359349672eae93255631f019c1c76ece9"],"state_sha256":"19ffe4ea7b70e5952489a633ae710f7159fb8917f41723cfb52afaaf8fa44e63"}