{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J2G3RLO5CTERL36U5VTA636CWJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ff7461de0384c7db9cdeb13a8d07b551e688c96f61d13db834507c69b0a090b2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T21:08:07Z","title_canon_sha256":"cccd8100e49f111a7f6aca95e75a0d51f77dfaf96df6ece4cf9986528155fe6d"},"schema_version":"1.0","source":{"id":"2410.23463","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23463","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23463v3","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23463","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"J2G3RLO5CTER","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"J2G3RLO5CTERL36U","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"J2G3RLO5","created_at":"2026-07-05T10:55:25Z"}],"graph_snapshots":[{"event_id":"sha256:eb707c1b6263f94e3d9d071795b0cef1362a7a17db9a4f3f50315282737f6f0d","target":"graph","created_at":"2026-07-05T10:55:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arman Cohan, Avi Caciularu, Bowen Shi, Gabrielle Kaili-May Liu, Idan Szpektor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T21:08:07Z","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23463","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab054c9f0a33260d966c0e3b62733f95e3f5d27a626ce052b56eeee186e1fce1","target":"record","created_at":"2026-07-05T10:55:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ff7461de0384c7db9cdeb13a8d07b551e688c96f61d13db834507c69b0a090b2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T21:08:07Z","title_canon_sha256":"cccd8100e49f111a7f6aca95e75a0d51f77dfaf96df6ece4cf9986528155fe6d"},"schema_version":"1.0","source":{"id":"2410.23463","kind":"arxiv","version":3}},"canonical_sha256":"4e8db8addd14c915efd4ed660f6fc2b25ad952ae4dd0311924d35261a3c61ce9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e8db8addd14c915efd4ed660f6fc2b25ad952ae4dd0311924d35261a3c61ce9","first_computed_at":"2026-07-05T10:55:25.351704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:25.351704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JgcZ05FtozP+6cL6/+VQOL8qGMioW/2Cdci4vsFZC8YKQupenqVhvfd4cSUkLFjKXscNCk87LmxAYs53g7F+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:25.352255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23463","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab054c9f0a33260d966c0e3b62733f95e3f5d27a626ce052b56eeee186e1fce1","sha256:eb707c1b6263f94e3d9d071795b0cef1362a7a17db9a4f3f50315282737f6f0d"],"state_sha256":"e1b2d6227f2a24ea21820360d52d65b62a26fb65f83ac67987c0442fd74312a7"}