{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BT4QT6OYOHYAMGNJIIGRINGZSG","short_pith_number":"pith:BT4QT6OY","schema_version":"1.0","canonical_sha256":"0cf909f9d871f00619a9420d1434d991a5e66a822906e285d4c19b2fa6cb607c","source":{"kind":"arxiv","id":"2208.00748","version":3},"attestation_state":"computed","paper":{"title":"Efficient Long-Text Understanding with Short-Text Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonathan Berant, Maor Ivgi, Uri Shaham","submitted_at":"2022-08-01T11:14:39Z","abstract_excerpt":"Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles and long documents, due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we p"},"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":"2208.00748","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-01T11:14:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"50870fab3897ff6d5ec4b446284e20497d23eb89c48f882c6ba26c2cd20c4be8","abstract_canon_sha256":"615143defae40116948fd2a41cf46c04882cde905d59146db94532a7a7ae8625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:46.565351Z","signature_b64":"NUIEJBRyDgBP9ye9pBJio5iNVitYFXvDq3smU9Obl7ZAKkY0guOTGb+SV0NLY21/K/YYiVDkKDevTSnQKCuADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cf909f9d871f00619a9420d1434d991a5e66a822906e285d4c19b2fa6cb607c","last_reissued_at":"2026-07-05T05:28:46.564941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:46.564941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Long-Text Understanding with Short-Text Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonathan Berant, Maor Ivgi, Uri Shaham","submitted_at":"2022-08-01T11:14:39Z","abstract_excerpt":"Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles and long documents, due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00748","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/2208.00748/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":"2208.00748","created_at":"2026-07-05T05:28:46.564997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00748v3","created_at":"2026-07-05T05:28:46.564997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00748","created_at":"2026-07-05T05:28:46.564997+00:00"},{"alias_kind":"pith_short_12","alias_value":"BT4QT6OYOHYA","created_at":"2026-07-05T05:28:46.564997+00:00"},{"alias_kind":"pith_short_16","alias_value":"BT4QT6OYOHYAMGNJ","created_at":"2026-07-05T05:28:46.564997+00:00"},{"alias_kind":"pith_short_8","alias_value":"BT4QT6OY","created_at":"2026-07-05T05:28:46.564997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18444","citing_title":"Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG","json":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG.json","graph_json":"https://pith.science/api/pith-number/BT4QT6OYOHYAMGNJIIGRINGZSG/graph.json","events_json":"https://pith.science/api/pith-number/BT4QT6OYOHYAMGNJIIGRINGZSG/events.json","paper":"https://pith.science/paper/BT4QT6OY"},"agent_actions":{"view_html":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG","download_json":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG.json","view_paper":"https://pith.science/paper/BT4QT6OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00748&json=true","fetch_graph":"https://pith.science/api/pith-number/BT4QT6OYOHYAMGNJIIGRINGZSG/graph.json","fetch_events":"https://pith.science/api/pith-number/BT4QT6OYOHYAMGNJIIGRINGZSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG/action/storage_attestation","attest_author":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG/action/author_attestation","sign_citation":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG/action/citation_signature","submit_replication":"https://pith.science/pith/BT4QT6OYOHYAMGNJIIGRINGZSG/action/replication_record"}},"created_at":"2026-07-05T05:28:46.564997+00:00","updated_at":"2026-07-05T05:28:46.564997+00:00"}