{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2T47RWWWFTOJUAJE4RIDU3Z6OA","short_pith_number":"pith:2T47RWWW","schema_version":"1.0","canonical_sha256":"d4f9f8dad62cdc9a0124e4503a6f3e700630e19a89b336af0786700f22abb4c7","source":{"kind":"arxiv","id":"2308.13191","version":2},"attestation_state":"computed","paper":{"title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawen Xie, Nan Du, Pengyu Cheng, Xiao Liang, Yong Dai","submitted_at":"2023-08-25T05:52:05Z","abstract_excerpt":"Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the input sequence length. To alleviate the complexity of long-sequence processing, we propose a simple framework to enable the offthe-shelf pre-trained transformers to process much longer sequences, while the computation and memory costs remain growing linearly with the input sequence lengths. More specifically, our method divides each long-sequence input into "},"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":"2308.13191","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T05:52:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6963ed6b93fac09abe2ae828ed00dc2365b5b6aa5b245a379f7f5876d947836","abstract_canon_sha256":"06440894e1684ab9dbb11e56d67da4803a24e86b4492e6d86b57d790cc269aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:08.455517Z","signature_b64":"a44AZ22jeqSJo7zHgsrS5QoMS7XL/il1Dqyl35/0J2tW0Ji0QlOixq6Z9Qf0vx1XlWFDgDvK5nIozb8G+YT8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f9f8dad62cdc9a0124e4503a6f3e700630e19a89b336af0786700f22abb4c7","last_reissued_at":"2026-07-05T08:40:08.455007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:08.455007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawen Xie, Nan Du, Pengyu Cheng, Xiao Liang, Yong Dai","submitted_at":"2023-08-25T05:52:05Z","abstract_excerpt":"Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the input sequence length. To alleviate the complexity of long-sequence processing, we propose a simple framework to enable the offthe-shelf pre-trained transformers to process much longer sequences, while the computation and memory costs remain growing linearly with the input sequence lengths. More specifically, our method divides each long-sequence input into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13191","kind":"arxiv","version":2},"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/2308.13191/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":"2308.13191","created_at":"2026-07-05T08:40:08.455069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13191v2","created_at":"2026-07-05T08:40:08.455069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13191","created_at":"2026-07-05T08:40:08.455069+00:00"},{"alias_kind":"pith_short_12","alias_value":"2T47RWWWFTOJ","created_at":"2026-07-05T08:40:08.455069+00:00"},{"alias_kind":"pith_short_16","alias_value":"2T47RWWWFTOJUAJE","created_at":"2026-07-05T08:40:08.455069+00:00"},{"alias_kind":"pith_short_8","alias_value":"2T47RWWW","created_at":"2026-07-05T08:40:08.455069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08506","citing_title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","ref_index":155,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA","json":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA.json","graph_json":"https://pith.science/api/pith-number/2T47RWWWFTOJUAJE4RIDU3Z6OA/graph.json","events_json":"https://pith.science/api/pith-number/2T47RWWWFTOJUAJE4RIDU3Z6OA/events.json","paper":"https://pith.science/paper/2T47RWWW"},"agent_actions":{"view_html":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA","download_json":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA.json","view_paper":"https://pith.science/paper/2T47RWWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13191&json=true","fetch_graph":"https://pith.science/api/pith-number/2T47RWWWFTOJUAJE4RIDU3Z6OA/graph.json","fetch_events":"https://pith.science/api/pith-number/2T47RWWWFTOJUAJE4RIDU3Z6OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA/action/storage_attestation","attest_author":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA/action/author_attestation","sign_citation":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA/action/citation_signature","submit_replication":"https://pith.science/pith/2T47RWWWFTOJUAJE4RIDU3Z6OA/action/replication_record"}},"created_at":"2026-07-05T08:40:08.455069+00:00","updated_at":"2026-07-05T08:40:08.455069+00:00"}