{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DMPIUPXNILR4J3OM7YGHDMQRUO","short_pith_number":"pith:DMPIUPXN","schema_version":"1.0","canonical_sha256":"1b1e8a3eed42e3c4edccfe0c71b211a38c19577961ab31f88ab1988c319a4442","source":{"kind":"arxiv","id":"2302.14502","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Long Text Modeling with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junyi Li, Tianyi Tang, Wayne Xin Zhao, Zican Dong","submitted_at":"2023-02-28T11:34:30Z","abstract_excerpt":"Modeling long texts has been an essential technique in the field of natural language processing (NLP). With the ever-growing number of long documents, it is important to develop effective modeling methods that can process and analyze such texts. However, long texts pose important research challenges for existing text models, with more complex semantics and special characteristics. In this paper, we provide an overview of the recent advances on long texts modeling based on Transformer models. Firstly, we introduce the formal definition of long text modeling. Then, as the core content, we discus"},"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":"2302.14502","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T11:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"bcc94720d2cd741f36a7c4e1786fad37cf3f7baa1ca95629509ebf9ee7391312","abstract_canon_sha256":"8c8fcd8d1a8c078655d2aa2cba69d0d50a278a8e64b756b6f09188ab76aa6345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:38.046948Z","signature_b64":"YUrzzx/zoN3pz5cOhL/j1RixjVFWYdak2mT3aepyxGGms96s4HYn8fueBrXEgiagQqeO5KUBgevhLG2jh3aVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1e8a3eed42e3c4edccfe0c71b211a38c19577961ab31f88ab1988c319a4442","last_reissued_at":"2026-07-05T11:18:38.046353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:38.046353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Long Text Modeling with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junyi Li, Tianyi Tang, Wayne Xin Zhao, Zican Dong","submitted_at":"2023-02-28T11:34:30Z","abstract_excerpt":"Modeling long texts has been an essential technique in the field of natural language processing (NLP). With the ever-growing number of long documents, it is important to develop effective modeling methods that can process and analyze such texts. However, long texts pose important research challenges for existing text models, with more complex semantics and special characteristics. In this paper, we provide an overview of the recent advances on long texts modeling based on Transformer models. Firstly, we introduce the formal definition of long text modeling. Then, as the core content, we discus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14502","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/2302.14502/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":"2302.14502","created_at":"2026-07-05T11:18:38.046423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14502v2","created_at":"2026-07-05T11:18:38.046423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14502","created_at":"2026-07-05T11:18:38.046423+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMPIUPXNILR4","created_at":"2026-07-05T11:18:38.046423+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMPIUPXNILR4J3OM","created_at":"2026-07-05T11:18:38.046423+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMPIUPXN","created_at":"2026-07-05T11:18:38.046423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2310.08560","citing_title":"MemGPT: Towards LLMs as Operating Systems","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO","json":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO.json","graph_json":"https://pith.science/api/pith-number/DMPIUPXNILR4J3OM7YGHDMQRUO/graph.json","events_json":"https://pith.science/api/pith-number/DMPIUPXNILR4J3OM7YGHDMQRUO/events.json","paper":"https://pith.science/paper/DMPIUPXN"},"agent_actions":{"view_html":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO","download_json":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO.json","view_paper":"https://pith.science/paper/DMPIUPXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14502&json=true","fetch_graph":"https://pith.science/api/pith-number/DMPIUPXNILR4J3OM7YGHDMQRUO/graph.json","fetch_events":"https://pith.science/api/pith-number/DMPIUPXNILR4J3OM7YGHDMQRUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO/action/storage_attestation","attest_author":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO/action/author_attestation","sign_citation":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO/action/citation_signature","submit_replication":"https://pith.science/pith/DMPIUPXNILR4J3OM7YGHDMQRUO/action/replication_record"}},"created_at":"2026-07-05T11:18:38.046423+00:00","updated_at":"2026-07-05T11:18:38.046423+00:00"}