{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GUNUZLRYL7HRJC4MMEDBOH7X33","short_pith_number":"pith:GUNUZLRY","schema_version":"1.0","canonical_sha256":"351b4cae385fcf148b8c6106171ff7def5ff431850757ffc99432970fed4f8ec","source":{"kind":"arxiv","id":"2402.07859","version":2},"attestation_state":"computed","paper":{"title":"Lissard: Long and Simple Sequential Reasoning Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mirelle Bueno, Roberto Lotufo, Rodrigo Nogueira","submitted_at":"2024-02-12T18:10:17Z","abstract_excerpt":"Language models are now capable of solving tasks that require dealing with long sequences consisting of hundreds of thousands of tokens. However, they often fail on tasks that require repetitive use of simple rules, even on sequences that are much shorter than those seen during training. For example, state-of-the-art LLMs can find common items in two lists with up to 20 items but fail when lists have 80 items. In this paper, we introduce Lissard, a benchmark comprising seven tasks whose goal is to assess the ability of models to process and generate wide-range sequence lengths, requiring repet"},"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":"2402.07859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T18:10:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"176dad195f6f91930279091ea2ffb39561dd24b83c1b889263f3719ac3430011","abstract_canon_sha256":"c089b0e78fd45da449c08da58c7cf1a73f346403006d40342fd2f334585c6e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:09.172325Z","signature_b64":"nGtFsQABg49cGV87nowfxCEiswNb/Sny4aypykYKNN2C/KjbgENyBuI23FJxAxBIZBQkhC9ndTlHQEQipQOXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"351b4cae385fcf148b8c6106171ff7def5ff431850757ffc99432970fed4f8ec","last_reissued_at":"2026-07-05T07:47:09.171863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:09.171863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lissard: Long and Simple Sequential Reasoning Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mirelle Bueno, Roberto Lotufo, Rodrigo Nogueira","submitted_at":"2024-02-12T18:10:17Z","abstract_excerpt":"Language models are now capable of solving tasks that require dealing with long sequences consisting of hundreds of thousands of tokens. However, they often fail on tasks that require repetitive use of simple rules, even on sequences that are much shorter than those seen during training. For example, state-of-the-art LLMs can find common items in two lists with up to 20 items but fail when lists have 80 items. In this paper, we introduce Lissard, a benchmark comprising seven tasks whose goal is to assess the ability of models to process and generate wide-range sequence lengths, requiring repet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07859","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/2402.07859/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":"2402.07859","created_at":"2026-07-05T07:47:09.171921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07859v2","created_at":"2026-07-05T07:47:09.171921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07859","created_at":"2026-07-05T07:47:09.171921+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUNUZLRYL7HR","created_at":"2026-07-05T07:47:09.171921+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUNUZLRYL7HRJC4M","created_at":"2026-07-05T07:47:09.171921+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUNUZLRY","created_at":"2026-07-05T07:47:09.171921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33","json":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33.json","graph_json":"https://pith.science/api/pith-number/GUNUZLRYL7HRJC4MMEDBOH7X33/graph.json","events_json":"https://pith.science/api/pith-number/GUNUZLRYL7HRJC4MMEDBOH7X33/events.json","paper":"https://pith.science/paper/GUNUZLRY"},"agent_actions":{"view_html":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33","download_json":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33.json","view_paper":"https://pith.science/paper/GUNUZLRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07859&json=true","fetch_graph":"https://pith.science/api/pith-number/GUNUZLRYL7HRJC4MMEDBOH7X33/graph.json","fetch_events":"https://pith.science/api/pith-number/GUNUZLRYL7HRJC4MMEDBOH7X33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33/action/storage_attestation","attest_author":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33/action/author_attestation","sign_citation":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33/action/citation_signature","submit_replication":"https://pith.science/pith/GUNUZLRYL7HRJC4MMEDBOH7X33/action/replication_record"}},"created_at":"2026-07-05T07:47:09.171921+00:00","updated_at":"2026-07-05T07:47:09.171921+00:00"}