{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6UH7EGJORPNFNZLAT3AT5OR5BL","short_pith_number":"pith:6UH7EGJO","schema_version":"1.0","canonical_sha256":"f50ff2192e8bda56e5609ec13eba3d0af8ca133ca792cbcd16f87103bf59874d","source":{"kind":"arxiv","id":"2406.16086","version":1},"attestation_state":"computed","paper":{"title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arie Cattan, Avi Caciularu, Gabriel Stanovsky, Gili Lior, Ori Shapira, Shahar Levy","submitted_at":"2024-06-23T11:57:53Z","abstract_excerpt":"Various tasks, such as summarization, multi-hop question answering, or coreference resolution, are naturally phrased over collections of real-world documents. Such tasks present a unique set of challenges, revolving around the lack of coherent narrative structure across documents, which often leads to contradiction, omission, or repetition of information. Despite their real-world application and challenging properties, there is currently no benchmark which specifically measures the abilities of large language models (LLMs) on multi-document tasks. To bridge this gap, we present SEAM (a Stochas"},"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":"2406.16086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-23T11:57:53Z","cross_cats_sorted":[],"title_canon_sha256":"15d6b37d853e92d1261d0cfaaa141bfd442d298748d1a24d0c09af03f4044878","abstract_canon_sha256":"f23e5b7a50d81602f95cbb670caf06446472d69bd7dd71b500171ee98358f6fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:53.127156Z","signature_b64":"gtm9gVgWmDQqZypHQvBGKTGedpWQs7dQnICJ9fLreamT7DWa+Cxdwzm0pRVeuh3L/KtYSJwNrdXuUVDgMn/4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f50ff2192e8bda56e5609ec13eba3d0af8ca133ca792cbcd16f87103bf59874d","last_reissued_at":"2026-07-05T08:35:53.126698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:53.126698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arie Cattan, Avi Caciularu, Gabriel Stanovsky, Gili Lior, Ori Shapira, Shahar Levy","submitted_at":"2024-06-23T11:57:53Z","abstract_excerpt":"Various tasks, such as summarization, multi-hop question answering, or coreference resolution, are naturally phrased over collections of real-world documents. Such tasks present a unique set of challenges, revolving around the lack of coherent narrative structure across documents, which often leads to contradiction, omission, or repetition of information. Despite their real-world application and challenging properties, there is currently no benchmark which specifically measures the abilities of large language models (LLMs) on multi-document tasks. To bridge this gap, we present SEAM (a Stochas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16086","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/2406.16086/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":"2406.16086","created_at":"2026-07-05T08:35:53.126755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16086v1","created_at":"2026-07-05T08:35:53.126755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16086","created_at":"2026-07-05T08:35:53.126755+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UH7EGJORPNF","created_at":"2026-07-05T08:35:53.126755+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UH7EGJORPNFNZLA","created_at":"2026-07-05T08:35:53.126755+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UH7EGJO","created_at":"2026-07-05T08:35:53.126755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13131","citing_title":"MM-Telco: Benchmarks and Multimodal Large Language Models for Telecom Applications","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL","json":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL.json","graph_json":"https://pith.science/api/pith-number/6UH7EGJORPNFNZLAT3AT5OR5BL/graph.json","events_json":"https://pith.science/api/pith-number/6UH7EGJORPNFNZLAT3AT5OR5BL/events.json","paper":"https://pith.science/paper/6UH7EGJO"},"agent_actions":{"view_html":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL","download_json":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL.json","view_paper":"https://pith.science/paper/6UH7EGJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16086&json=true","fetch_graph":"https://pith.science/api/pith-number/6UH7EGJORPNFNZLAT3AT5OR5BL/graph.json","fetch_events":"https://pith.science/api/pith-number/6UH7EGJORPNFNZLAT3AT5OR5BL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL/action/storage_attestation","attest_author":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL/action/author_attestation","sign_citation":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL/action/citation_signature","submit_replication":"https://pith.science/pith/6UH7EGJORPNFNZLAT3AT5OR5BL/action/replication_record"}},"created_at":"2026-07-05T08:35:53.126755+00:00","updated_at":"2026-07-05T08:35:53.126755+00:00"}