{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5LF47DFV4LLX26VGAGHTBKCT3M","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":"13a8f0306ed7c5bf5b3b9904157cb1e1a2697775683c3a32632beec96dc3e5d1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T17:23:21Z","title_canon_sha256":"92d52d9d155cec60decb81ad1ae910fac9323db70aded2b9965ea5314f1526be"},"schema_version":"1.0","source":{"id":"2406.15319","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15319","created_at":"2026-07-05T09:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15319v3","created_at":"2026-07-05T09:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15319","created_at":"2026-07-05T09:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"5LF47DFV4LLX","created_at":"2026-07-05T09:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"5LF47DFV4LLX26VG","created_at":"2026-07-05T09:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"5LF47DFV","created_at":"2026-07-05T09:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:e04981d0377401262806ad4bdcf756764a40c22ab128d8ddaee4f25dc932f537","target":"graph","created_at":"2026-07-05T09:01:35Z","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/2406.15319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In traditional RAG framework, the basic retrieval units are normally short. The common retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design forces the retriever to search over a large corpus to find the `needle' unit. In contrast, the readers only need to generate answers from the short retrieved units. The imbalanced `heavy' retriever and `light' reader design can lead to sub-optimal performance. The loss of contextual information in the short, chunked units may increase the likelihood of introducing hard negatives during the retrieval stage. Additionally, the r","authors_text":"Wenhu Chen, Xueguang Ma, Ziyan Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T17:23:21Z","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15319","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":"sha256:69948b145d482049df010e00954dae83eec1dbaf7e99c79b104e5b1fa1fee46b","target":"record","created_at":"2026-07-05T09:01:35Z","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":"13a8f0306ed7c5bf5b3b9904157cb1e1a2697775683c3a32632beec96dc3e5d1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T17:23:21Z","title_canon_sha256":"92d52d9d155cec60decb81ad1ae910fac9323db70aded2b9965ea5314f1526be"},"schema_version":"1.0","source":{"id":"2406.15319","kind":"arxiv","version":3}},"canonical_sha256":"eacbcf8cb5e2d77d7aa6018f30a853db0b3ea3054304e90d799d4307c152265e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eacbcf8cb5e2d77d7aa6018f30a853db0b3ea3054304e90d799d4307c152265e","first_computed_at":"2026-07-05T09:01:35.558981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:35.558981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6quca0pxQk3kT1/rw0PS1Xq2Z07TGxvc9ANSgV31mTxr1jg8xrgPthJZe9Ii73+1FHvhFKR2yxfK11edIrvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:35.559516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15319","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69948b145d482049df010e00954dae83eec1dbaf7e99c79b104e5b1fa1fee46b","sha256:e04981d0377401262806ad4bdcf756764a40c22ab128d8ddaee4f25dc932f537"],"state_sha256":"463fc79a6d4e3fdb77ea8a44385bcbead1b3224305b142084368351fd571a8d9"}