{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3DYRUTUEKQUGFJPDGSN4FHTD6","short_pith_number":"pith:K3DYRUTU","schema_version":"1.0","canonical_sha256":"56c788d27422a143152f19a4de14f31f8eaf78597b9bfe1ba2615f0df892d548","source":{"kind":"arxiv","id":"2507.12143","version":1},"attestation_state":"computed","paper":{"title":"Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Bojar, Pavel \\v{S}indel\\'a\\v{r}","submitted_at":"2025-07-16T11:19:28Z","abstract_excerpt":"ELOQUENT is a set of shared tasks that aims to create easily testable high-level criteria for evaluating generative language models. Sensemaking is one such shared task.\n  In Sensemaking, we try to assess how well generative models ``make sense out of a given text'' in three steps inspired by exams in a classroom setting: (1) Teacher systems should prepare a set of questions, (2) Student systems should answer these questions, and (3) Evaluator systems should score these answers, all adhering rather strictly to a given set of input materials.\n  We report on the 2025 edition of Sensemaking, wher"},"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":"2507.12143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T11:19:28Z","cross_cats_sorted":[],"title_canon_sha256":"59285b4bc2451ee0399af8e6027805f9d756d507a6a14ae8457952b3f1105490","abstract_canon_sha256":"756abc54b29d975feb6408fe278e9878e420092e8e29d5c4b784bd96979f5236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:15.378300Z","signature_b64":"tVxmIpQgpY3774mKzu9UYceipFb4IouJKr8CdzxxxEQelDVGeaEPcEzdMyyqgNrFEMXJtb8mYke/Jq76m/7vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56c788d27422a143152f19a4de14f31f8eaf78597b9bfe1ba2615f0df892d548","last_reissued_at":"2026-07-05T11:38:15.377782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:15.377782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Bojar, Pavel \\v{S}indel\\'a\\v{r}","submitted_at":"2025-07-16T11:19:28Z","abstract_excerpt":"ELOQUENT is a set of shared tasks that aims to create easily testable high-level criteria for evaluating generative language models. Sensemaking is one such shared task.\n  In Sensemaking, we try to assess how well generative models ``make sense out of a given text'' in three steps inspired by exams in a classroom setting: (1) Teacher systems should prepare a set of questions, (2) Student systems should answer these questions, and (3) Evaluator systems should score these answers, all adhering rather strictly to a given set of input materials.\n  We report on the 2025 edition of Sensemaking, wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12143","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/2507.12143/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":"2507.12143","created_at":"2026-07-05T11:38:15.377844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12143v1","created_at":"2026-07-05T11:38:15.377844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12143","created_at":"2026-07-05T11:38:15.377844+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3DYRUTUEKQU","created_at":"2026-07-05T11:38:15.377844+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3DYRUTUEKQUGFJP","created_at":"2026-07-05T11:38:15.377844+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3DYRUTU","created_at":"2026-07-05T11:38:15.377844+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/K3DYRUTUEKQUGFJPDGSN4FHTD6","json":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6.json","graph_json":"https://pith.science/api/pith-number/K3DYRUTUEKQUGFJPDGSN4FHTD6/graph.json","events_json":"https://pith.science/api/pith-number/K3DYRUTUEKQUGFJPDGSN4FHTD6/events.json","paper":"https://pith.science/paper/K3DYRUTU"},"agent_actions":{"view_html":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6","download_json":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6.json","view_paper":"https://pith.science/paper/K3DYRUTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12143&json=true","fetch_graph":"https://pith.science/api/pith-number/K3DYRUTUEKQUGFJPDGSN4FHTD6/graph.json","fetch_events":"https://pith.science/api/pith-number/K3DYRUTUEKQUGFJPDGSN4FHTD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6/action/storage_attestation","attest_author":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6/action/author_attestation","sign_citation":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6/action/citation_signature","submit_replication":"https://pith.science/pith/K3DYRUTUEKQUGFJPDGSN4FHTD6/action/replication_record"}},"created_at":"2026-07-05T11:38:15.377844+00:00","updated_at":"2026-07-05T11:38:15.377844+00:00"}