{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QCRIXGWFC7KS65JW2R52E7W7G2","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":"294a279c01343c2095ad5ccb58a47a99bbb7d15734e89a1c72f0bebd7ece87ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:27:30Z","title_canon_sha256":"01cf89018f7aa01233eba097b382a67fad683c4d23aea828f8affb04760dea90"},"schema_version":"1.0","source":{"id":"2410.02703","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02703","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02703v2","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02703","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_12","alias_value":"QCRIXGWFC7KS","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_16","alias_value":"QCRIXGWFC7KS65JW","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_8","alias_value":"QCRIXGWF","created_at":"2026-07-05T10:53:12Z"}],"graph_snapshots":[{"event_id":"sha256:1bf7a3c3df5a4a77033eec118dc48841f4e96ccd2443bc3c6e711f92b3f52fe1","target":"graph","created_at":"2026-07-05T10:53:12Z","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/2410.02703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention consistently improves language modeling and downstream task performance in a variety of model sizes and context lengths. For example, transformers trained with the language modeling objective on C4 with selective attention perform language modeling equivalently to standard transformers with ~2X more heads and parameters in their attention modules. Selective attenti","authors_text":"Matan Kalman, Yaniv Leviathan, Yossi Matias","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:27:30Z","title":"Selective Attention Improves Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02703","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:ec3026266e50827cec4d264c853ee3ff7dfd22eaab325039288636778280c9fe","target":"record","created_at":"2026-07-05T10:53:12Z","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":"294a279c01343c2095ad5ccb58a47a99bbb7d15734e89a1c72f0bebd7ece87ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:27:30Z","title_canon_sha256":"01cf89018f7aa01233eba097b382a67fad683c4d23aea828f8affb04760dea90"},"schema_version":"1.0","source":{"id":"2410.02703","kind":"arxiv","version":2}},"canonical_sha256":"80a28b9ac517d52f7536d47ba27edf36b707f2f4c631d92294c11b1d4dc78208","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80a28b9ac517d52f7536d47ba27edf36b707f2f4c631d92294c11b1d4dc78208","first_computed_at":"2026-07-05T10:53:12.198018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:12.198018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rjHpFFN+djBvOFWkcMhp1VF8YdpKoUSTkLV7JxSPggh56d4s6Kptonl3loLnaCZFMoDPLtg6T0SNpXDWF1b0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:12.198494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02703","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec3026266e50827cec4d264c853ee3ff7dfd22eaab325039288636778280c9fe","sha256:1bf7a3c3df5a4a77033eec118dc48841f4e96ccd2443bc3c6e711f92b3f52fe1"],"state_sha256":"e2e5f13207130c48ee140042140f392463a72e44447fcbb0e6d1fc779c540d90"}