{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XKSBDUDNJN2VPLGXCOWLNA44GO","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":"cdb9c8c94d4179282a277c5721e662bfdb8b247b04a7b78d52f75afc1748ed3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T04:46:20Z","title_canon_sha256":"4d674b486c8de326ed754f13d481cd9bf46f40dc53dd897c811d87cf2e04e7e9"},"schema_version":"1.0","source":{"id":"2412.00359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00359","created_at":"2026-07-05T10:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00359v2","created_at":"2026-07-05T10:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00359","created_at":"2026-07-05T10:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"XKSBDUDNJN2V","created_at":"2026-07-05T10:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"XKSBDUDNJN2VPLGX","created_at":"2026-07-05T10:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"XKSBDUDN","created_at":"2026-07-05T10:57:30Z"}],"graph_snapshots":[{"event_id":"sha256:f30448e1c61513627e19788242507bf9384c8287f879ff37e8ae354de13edc5a","target":"graph","created_at":"2026-07-05T10:57:30Z","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/2412.00359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent directionality. This work introduces a shared weight self-attention-based BERT model that only learns one weight matrix for (Key, Value, and Query) representations instead of three individual matrices for each of them. Our shared weight attention reduces the training parameter size by more than half and training time by around one-tenth. Furthermore, we demonstrate highe","authors_text":"Chun-Nam Yu, Md Kowsher, Niloofar Yousefi, Nusrat Jahan Prottasha, Ozlem Ozmen Garibay","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T04:46:20Z","title":"Does Self-Attention Need Separate Weights in Transformers?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00359","kind":"arxiv","version":2},"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":"sha256:8eed043fb4164a16686a9ce330349c3acd77d4780ccd3fd89c1fd9d27f0c216c","target":"record","created_at":"2026-07-05T10:57:30Z","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":"cdb9c8c94d4179282a277c5721e662bfdb8b247b04a7b78d52f75afc1748ed3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T04:46:20Z","title_canon_sha256":"4d674b486c8de326ed754f13d481cd9bf46f40dc53dd897c811d87cf2e04e7e9"},"schema_version":"1.0","source":{"id":"2412.00359","kind":"arxiv","version":2}},"canonical_sha256":"baa411d06d4b7557acd713acb6839c33a9afd1b90b65cdc47c9fbd5a544479d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baa411d06d4b7557acd713acb6839c33a9afd1b90b65cdc47c9fbd5a544479d1","first_computed_at":"2026-07-05T10:57:30.096248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:30.096248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVwyugi+9dbqZORme9bkb+8ranierTcd3OBag+YK8XBmbw8uwmE3jNhvVEdviRsDI8syszaULpWb/ZJN7wGrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:30.096798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eed043fb4164a16686a9ce330349c3acd77d4780ccd3fd89c1fd9d27f0c216c","sha256:f30448e1c61513627e19788242507bf9384c8287f879ff37e8ae354de13edc5a"],"state_sha256":"48d795bd69b66f2bdf179828e2d78072ad3bf0cd2a413f52e503444d61e510bc"}