{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LXAG66MORRABIZXCVJLT2T2P7T","short_pith_number":"pith:LXAG66MO","schema_version":"1.0","canonical_sha256":"5dc06f798e8c401466e2aa573d4f4ffce98bcb1c20600f9569021095873b7ae0","source":{"kind":"arxiv","id":"2401.17919","version":3},"attestation_state":"computed","paper":{"title":"LOCOST: State-Space Models for Long Document Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alberto Lumbreras, Alexandre Allauzen, Florian Le Bronnec, Laure Soulier, Mathieu Ravaut, Nancy F. Chen, Patrick Gallinari, Song Duong, Vincent Guigue","submitted_at":"2024-01-31T15:33:37Z","abstract_excerpt":"State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text generation with long context inputs. With a computational complexity of $O(L \\log L)$, this architecture can handle significantly longer sequences than state-of-the-art models that are based on sparse attention patterns. We evaluate our model on a series of long document abstractive summarization tasks. The model reaches a performance level that is 93-96% comparab"},"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":"2401.17919","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T15:33:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f689abf483520f630febec026efe99bbee57cc6c031bef1050dade8932462a9","abstract_canon_sha256":"60738bb1a147d4bf05e62196b9243599d5bac0c7961138af733276cfec84e4f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:00.853272Z","signature_b64":"lu6UVlqjEbrfD8ETaFj+uN9uO8UFLWc80wBMkPVor+i99tGe8fHccqhBm5EgJUc/yFZEbajJwAgi8Lbn839qDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc06f798e8c401466e2aa573d4f4ffce98bcb1c20600f9569021095873b7ae0","last_reissued_at":"2026-07-05T08:00:00.852786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:00.852786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOCOST: State-Space Models for Long Document Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alberto Lumbreras, Alexandre Allauzen, Florian Le Bronnec, Laure Soulier, Mathieu Ravaut, Nancy F. Chen, Patrick Gallinari, Song Duong, Vincent Guigue","submitted_at":"2024-01-31T15:33:37Z","abstract_excerpt":"State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text generation with long context inputs. With a computational complexity of $O(L \\log L)$, this architecture can handle significantly longer sequences than state-of-the-art models that are based on sparse attention patterns. We evaluate our model on a series of long document abstractive summarization tasks. The model reaches a performance level that is 93-96% comparab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17919","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/2401.17919/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":"2401.17919","created_at":"2026-07-05T08:00:00.852846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17919v3","created_at":"2026-07-05T08:00:00.852846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17919","created_at":"2026-07-05T08:00:00.852846+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXAG66MORRAB","created_at":"2026-07-05T08:00:00.852846+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXAG66MORRABIZXC","created_at":"2026-07-05T08:00:00.852846+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXAG66MO","created_at":"2026-07-05T08:00:00.852846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T","json":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T.json","graph_json":"https://pith.science/api/pith-number/LXAG66MORRABIZXCVJLT2T2P7T/graph.json","events_json":"https://pith.science/api/pith-number/LXAG66MORRABIZXCVJLT2T2P7T/events.json","paper":"https://pith.science/paper/LXAG66MO"},"agent_actions":{"view_html":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T","download_json":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T.json","view_paper":"https://pith.science/paper/LXAG66MO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17919&json=true","fetch_graph":"https://pith.science/api/pith-number/LXAG66MORRABIZXCVJLT2T2P7T/graph.json","fetch_events":"https://pith.science/api/pith-number/LXAG66MORRABIZXCVJLT2T2P7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T/action/storage_attestation","attest_author":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T/action/author_attestation","sign_citation":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T/action/citation_signature","submit_replication":"https://pith.science/pith/LXAG66MORRABIZXCVJLT2T2P7T/action/replication_record"}},"created_at":"2026-07-05T08:00:00.852846+00:00","updated_at":"2026-07-05T08:00:00.852846+00:00"}