{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J2G3RLO5CTERL36U5VTA636CWJ","short_pith_number":"pith:J2G3RLO5","schema_version":"1.0","canonical_sha256":"4e8db8addd14c915efd4ed660f6fc2b25ad952ae4dd0311924d35261a3c61ce9","source":{"kind":"arxiv","id":"2410.23463","version":3},"attestation_state":"computed","paper":{"title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Avi Caciularu, Bowen Shi, Gabrielle Kaili-May Liu, Idan Szpektor","submitted_at":"2024-10-30T21:08:07Z","abstract_excerpt":"Multi-document (MD) processing is crucial for LLMs to handle real-world tasks such as summarization and question-answering across large sets of documents. While LLMs have improved at processing long inputs, MD contexts still present unique difficulties, including management of inter-document dependencies, redundancy, and incoherent structures. To address this challenge, we introduce MDCure, a scalable and effective instruction data generation framework to enhance the MD capabilities of LLMs without the computational cost of pre-training or reliance on human-annotated data. MDCure generates hig"},"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":"2410.23463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T21:08:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cccd8100e49f111a7f6aca95e75a0d51f77dfaf96df6ece4cf9986528155fe6d","abstract_canon_sha256":"ff7461de0384c7db9cdeb13a8d07b551e688c96f61d13db834507c69b0a090b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:25.352255Z","signature_b64":"JgcZ05FtozP+6cL6/+VQOL8qGMioW/2Cdci4vsFZC8YKQupenqVhvfd4cSUkLFjKXscNCk87LmxAYs53g7F+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e8db8addd14c915efd4ed660f6fc2b25ad952ae4dd0311924d35261a3c61ce9","last_reissued_at":"2026-07-05T10:55:25.351704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:25.351704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Avi Caciularu, Bowen Shi, Gabrielle Kaili-May Liu, Idan Szpektor","submitted_at":"2024-10-30T21:08:07Z","abstract_excerpt":"Multi-document (MD) processing is crucial for LLMs to handle real-world tasks such as summarization and question-answering across large sets of documents. While LLMs have improved at processing long inputs, MD contexts still present unique difficulties, including management of inter-document dependencies, redundancy, and incoherent structures. To address this challenge, we introduce MDCure, a scalable and effective instruction data generation framework to enhance the MD capabilities of LLMs without the computational cost of pre-training or reliance on human-annotated data. MDCure generates hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23463","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/2410.23463/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":"2410.23463","created_at":"2026-07-05T10:55:25.351795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23463v3","created_at":"2026-07-05T10:55:25.351795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23463","created_at":"2026-07-05T10:55:25.351795+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2G3RLO5CTER","created_at":"2026-07-05T10:55:25.351795+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2G3RLO5CTERL36U","created_at":"2026-07-05T10:55:25.351795+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2G3RLO5","created_at":"2026-07-05T10:55:25.351795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11166","citing_title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ","json":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ.json","graph_json":"https://pith.science/api/pith-number/J2G3RLO5CTERL36U5VTA636CWJ/graph.json","events_json":"https://pith.science/api/pith-number/J2G3RLO5CTERL36U5VTA636CWJ/events.json","paper":"https://pith.science/paper/J2G3RLO5"},"agent_actions":{"view_html":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ","download_json":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ.json","view_paper":"https://pith.science/paper/J2G3RLO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23463&json=true","fetch_graph":"https://pith.science/api/pith-number/J2G3RLO5CTERL36U5VTA636CWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/J2G3RLO5CTERL36U5VTA636CWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ/action/storage_attestation","attest_author":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ/action/author_attestation","sign_citation":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ/action/citation_signature","submit_replication":"https://pith.science/pith/J2G3RLO5CTERL36U5VTA636CWJ/action/replication_record"}},"created_at":"2026-07-05T10:55:25.351795+00:00","updated_at":"2026-07-05T10:55:25.351795+00:00"}