{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:73Z7U7QJP55DP47NQEUQZTKW4W","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":"1f7d9b809c3ff3094c645707793d8d51630d465bae452073e310f78d194db7a3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T22:48:08Z","title_canon_sha256":"85a911b3accdd3f0ae39e0ce9952acd9579846fa01eec2a4335b4fa8b618c060"},"schema_version":"1.0","source":{"id":"2306.09539","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09539","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09539v4","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09539","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"73Z7U7QJP55D","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"73Z7U7QJP55DP47N","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"73Z7U7QJ","created_at":"2026-07-05T07:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:a990a8a571e1b7de9112812e13d43043166023c753ddbe401ac0ddc54ffa32e0","target":"graph","created_at":"2026-07-05T07:06:30Z","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/2306.09539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic runtime complexity. Originally designed for continuous signals, SSMs have shown superior performance on a plethora of tasks, in vision and audio; however, SSMs still lag Transformer performance in Language Modeling tasks. In this work, we propose a hybrid layer named Block-State Transformer (BST), that internally combines an SSM sublayer for long-range contextualization, and a Block Transformer sublayer for short-term","authors_text":"Christopher Pal, Jonathan Pilault, Mahan Fathi, Orhan Firat, Pierre-Luc Bacon, Ross Goroshin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T22:48:08Z","title":"Block-State Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09539","kind":"arxiv","version":4},"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":"sha256:86fe0cdd8c57178660eaa09d961bfb485417c2b18234d07f263fc72167293bf4","target":"record","created_at":"2026-07-05T07:06:30Z","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":"1f7d9b809c3ff3094c645707793d8d51630d465bae452073e310f78d194db7a3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T22:48:08Z","title_canon_sha256":"85a911b3accdd3f0ae39e0ce9952acd9579846fa01eec2a4335b4fa8b618c060"},"schema_version":"1.0","source":{"id":"2306.09539","kind":"arxiv","version":4}},"canonical_sha256":"fef3fa7e097f7a37f3ed81290ccd56e58a9dba0e577850041c0471d86e0ad60d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fef3fa7e097f7a37f3ed81290ccd56e58a9dba0e577850041c0471d86e0ad60d","first_computed_at":"2026-07-05T07:06:30.265293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:30.265293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NrQ76SvaSPjT8Bw4/fw+3ZodubY9toJOoJSJORGj2dJs9ilf+TOUa47AtSUw3KYDejmcl2TexMaDQEqAJ8B2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:30.265784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09539","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86fe0cdd8c57178660eaa09d961bfb485417c2b18234d07f263fc72167293bf4","sha256:a990a8a571e1b7de9112812e13d43043166023c753ddbe401ac0ddc54ffa32e0"],"state_sha256":"1de4d1a773185da338d5a802c3ee71b7a10133457d9bde1c97c372ffcd5754cf"}