{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BDF23V2IKGEBEXDPML2GRNO7TA","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":"182d7139f6f0407c4a133f5f5a1f26eef37aebfecd7667db664ef4ae22eae891","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T08:16:19Z","title_canon_sha256":"f2da81d49fb63975091913af33fd072210ba8937101c78ccff49a94077b52f2d"},"schema_version":"1.0","source":{"id":"2005.00743","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00743","created_at":"2026-07-05T02:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00743v3","created_at":"2026-07-05T02:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00743","created_at":"2026-07-05T02:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"BDF23V2IKGEB","created_at":"2026-07-05T02:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"BDF23V2IKGEBEXDP","created_at":"2026-07-05T02:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"BDF23V2I","created_at":"2026-07-05T02:42:25Z"}],"graph_snapshots":[{"event_id":"sha256:85564d587fcf9a16e15c496851ad2555ec9d4bb137bc9e073f91f0908b9ac5cd","target":"graph","created_at":"2026-07-05T02:42:25Z","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/2005.00743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention mechanism on the performance of Transformer models. Via extensive experiments, we find that (1) random alignment matrices surprisingly perform quite competitively and (2) learning attention weights from token-token (query-key) interactions is useful but not that important after all. To this end, we propose \\textsc{Synthesizer}, a model that learns synthetic ","authors_text":"Che Zheng, Da-Cheng Juan, Dara Bahri, Donald Metzler, Yi Tay, Zhe Zhao","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T08:16:19Z","title":"Synthesizer: Rethinking Self-Attention in Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00743","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:e89d5c96c2192d18f280888b5d515fe9e3cf1a14ead6a230a242f9a40950ce33","target":"record","created_at":"2026-07-05T02:42:25Z","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":"182d7139f6f0407c4a133f5f5a1f26eef37aebfecd7667db664ef4ae22eae891","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T08:16:19Z","title_canon_sha256":"f2da81d49fb63975091913af33fd072210ba8937101c78ccff49a94077b52f2d"},"schema_version":"1.0","source":{"id":"2005.00743","kind":"arxiv","version":3}},"canonical_sha256":"08cbadd7485188125c6f62f468b5df983ce83e8d8d1437391562fc251817f58d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08cbadd7485188125c6f62f468b5df983ce83e8d8d1437391562fc251817f58d","first_computed_at":"2026-07-05T02:42:25.517278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:25.517278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5zefNyH83wIh4TSUN4u8Cxvn+SL/BbVToERBQk9MKkLqNsrqPm/fUpkqYMgGcFwo7yBJq6ANqjLklLosqxz8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:25.517720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00743","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e89d5c96c2192d18f280888b5d515fe9e3cf1a14ead6a230a242f9a40950ce33","sha256:85564d587fcf9a16e15c496851ad2555ec9d4bb137bc9e073f91f0908b9ac5cd"],"state_sha256":"3975505abeb336a88b110a2c173eca5de05147e6a2deeed631f9b4cf510c9e2f"}