{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XJQD7MN4XQCJJO67EQA7YJ2JCW","short_pith_number":"pith:XJQD7MN4","schema_version":"1.0","canonical_sha256":"ba603fb1bcbc0494bbdf2401fc274915abf24ada78c49b4d2bf2fff5644058b9","source":{"kind":"arxiv","id":"2305.19370","version":3},"attestation_state":"computed","paper":{"title":"Blockwise Parallel Transformer for Large Context Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Liu, Pieter Abbeel","submitted_at":"2023-05-30T19:25:51Z","abstract_excerpt":"Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention mechanism and the large feedforward network in Transformers limit their ability to handle long sequences, thereby creating challenges for tasks involving multiple long sequences or long-term dependencies. We present a distinct approach, Blockwise Parallel Transformer (BPT), that leverages blockwise computation of self-attention and feedforward network fusion to mini"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.19370","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T19:25:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c113c80493073019dcab42567bbb11fe1915f5e1990798c941c9e677aa575db","abstract_canon_sha256":"12f03d7b0eddc02e2615be16d4abc4204fb87e54f4f535542b2a1e88aad6d193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:36.465889Z","signature_b64":"pUXW6GrLkd67PH+dMRVuS5LY9gwDr5lyNcHRhbn3jzBmCijBWBwVbKrSkL/P8OxCJUs9QnnJVv4A8PqAiwgRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba603fb1bcbc0494bbdf2401fc274915abf24ada78c49b4d2bf2fff5644058b9","last_reissued_at":"2026-07-05T06:45:36.465418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:36.465418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blockwise Parallel Transformer for Large Context Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Liu, Pieter Abbeel","submitted_at":"2023-05-30T19:25:51Z","abstract_excerpt":"Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention mechanism and the large feedforward network in Transformers limit their ability to handle long sequences, thereby creating challenges for tasks involving multiple long sequences or long-term dependencies. We present a distinct approach, Blockwise Parallel Transformer (BPT), that leverages blockwise computation of self-attention and feedforward network fusion to mini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19370","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.19370/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.19370","created_at":"2026-07-05T06:45:36.465479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19370v3","created_at":"2026-07-05T06:45:36.465479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19370","created_at":"2026-07-05T06:45:36.465479+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJQD7MN4XQCJ","created_at":"2026-07-05T06:45:36.465479+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJQD7MN4XQCJJO67","created_at":"2026-07-05T06:45:36.465479+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJQD7MN4","created_at":"2026-07-05T06:45:36.465479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08587","citing_title":"Kaczmarz Linear Attention","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW","json":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW.json","graph_json":"https://pith.science/api/pith-number/XJQD7MN4XQCJJO67EQA7YJ2JCW/graph.json","events_json":"https://pith.science/api/pith-number/XJQD7MN4XQCJJO67EQA7YJ2JCW/events.json","paper":"https://pith.science/paper/XJQD7MN4"},"agent_actions":{"view_html":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW","download_json":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW.json","view_paper":"https://pith.science/paper/XJQD7MN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19370&json=true","fetch_graph":"https://pith.science/api/pith-number/XJQD7MN4XQCJJO67EQA7YJ2JCW/graph.json","fetch_events":"https://pith.science/api/pith-number/XJQD7MN4XQCJJO67EQA7YJ2JCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW/action/storage_attestation","attest_author":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW/action/author_attestation","sign_citation":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW/action/citation_signature","submit_replication":"https://pith.science/pith/XJQD7MN4XQCJJO67EQA7YJ2JCW/action/replication_record"}},"created_at":"2026-07-05T06:45:36.465479+00:00","updated_at":"2026-07-05T06:45:36.465479+00:00"}