{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPAXLAZHZZD6M3ALDPYLBK5YY3","short_pith_number":"pith:LPAXLAZH","schema_version":"1.0","canonical_sha256":"5bc1758327ce47e66c0b1bf0b0abb8c6e0570e74221073feb983cf8be469c58e","source":{"kind":"arxiv","id":"2501.12980","version":1},"attestation_state":"computed","paper":{"title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Florian Kankowski, Oliver Bott, Sina Zarriess, Torgrim Solstad","submitted_at":"2025-01-22T16:07:24Z","abstract_excerpt":"In this paper, we compare data generated with mono- and multilingual LLMs spanning a range of model sizes with data provided by human participants in an experimental setting investigating well-established discourse biases. Beyond the comparison as such, we aim to develop a benchmark to assess the capabilities of LLMs with discourse biases as a robust proxy for more general discourse understanding capabilities. More specifically, we investigated Implicit Causality verbs, for which psycholinguistic research has found participants to display biases with regard to three phenomena:\\ the establishme"},"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":"2501.12980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:07:24Z","cross_cats_sorted":[],"title_canon_sha256":"75c33141adea2ecffff75a0cf8569886b679f4c88cf002b1513f15bacfba8db0","abstract_canon_sha256":"d37342ea6bf4d2979e416c5402e2fb43ca388063347fe8c13ef2974c940084ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:01.289506Z","signature_b64":"F/sL5AvmAE/wRHAWe8gR5N26cC4mNWYa3vsYFaQf5NboH5guZXQICDMQ0r+oXywQnxsRXINW1PCmk+nNFZn2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc1758327ce47e66c0b1bf0b0abb8c6e0570e74221073feb983cf8be469c58e","last_reissued_at":"2026-07-05T10:04:01.289036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:01.289036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Florian Kankowski, Oliver Bott, Sina Zarriess, Torgrim Solstad","submitted_at":"2025-01-22T16:07:24Z","abstract_excerpt":"In this paper, we compare data generated with mono- and multilingual LLMs spanning a range of model sizes with data provided by human participants in an experimental setting investigating well-established discourse biases. Beyond the comparison as such, we aim to develop a benchmark to assess the capabilities of LLMs with discourse biases as a robust proxy for more general discourse understanding capabilities. More specifically, we investigated Implicit Causality verbs, for which psycholinguistic research has found participants to display biases with regard to three phenomena:\\ the establishme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12980","kind":"arxiv","version":1},"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/2501.12980/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":"2501.12980","created_at":"2026-07-05T10:04:01.289094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12980v1","created_at":"2026-07-05T10:04:01.289094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12980","created_at":"2026-07-05T10:04:01.289094+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPAXLAZHZZD6","created_at":"2026-07-05T10:04:01.289094+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPAXLAZHZZD6M3AL","created_at":"2026-07-05T10:04:01.289094+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPAXLAZH","created_at":"2026-07-05T10:04:01.289094+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/LPAXLAZHZZD6M3ALDPYLBK5YY3","json":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3.json","graph_json":"https://pith.science/api/pith-number/LPAXLAZHZZD6M3ALDPYLBK5YY3/graph.json","events_json":"https://pith.science/api/pith-number/LPAXLAZHZZD6M3ALDPYLBK5YY3/events.json","paper":"https://pith.science/paper/LPAXLAZH"},"agent_actions":{"view_html":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3","download_json":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3.json","view_paper":"https://pith.science/paper/LPAXLAZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12980&json=true","fetch_graph":"https://pith.science/api/pith-number/LPAXLAZHZZD6M3ALDPYLBK5YY3/graph.json","fetch_events":"https://pith.science/api/pith-number/LPAXLAZHZZD6M3ALDPYLBK5YY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3/action/storage_attestation","attest_author":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3/action/author_attestation","sign_citation":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3/action/citation_signature","submit_replication":"https://pith.science/pith/LPAXLAZHZZD6M3ALDPYLBK5YY3/action/replication_record"}},"created_at":"2026-07-05T10:04:01.289094+00:00","updated_at":"2026-07-05T10:04:01.289094+00:00"}