{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NE22UV5Z4L3OZHDAZGGKNQY56M","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":"9690f768aeec36ea99c7c01bc6fa67e2c5a5ca94899e6afefaded378f35a705e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T15:23:42Z","title_canon_sha256":"332786d0c99b2150b26ce4db55f2c03eb4863c926d56096f7485cded9fc9ff41"},"schema_version":"1.0","source":{"id":"2407.01370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01370","created_at":"2026-07-05T08:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01370v1","created_at":"2026-07-05T08:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01370","created_at":"2026-07-05T08:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"NE22UV5Z4L3O","created_at":"2026-07-05T08:38:47Z"},{"alias_kind":"pith_short_16","alias_value":"NE22UV5Z4L3OZHDA","created_at":"2026-07-05T08:38:47Z"},{"alias_kind":"pith_short_8","alias_value":"NE22UV5Z","created_at":"2026-07-05T08:38:47Z"}],"graph_snapshots":[{"event_id":"sha256:dd1437b556aacccfb72e7bbf6dc5bd6660c98adf44f949ab163705372b7e8f51","target":"graph","created_at":"2026-07-05T08:38:47Z","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/2407.01370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks remains challenging, as tasks like Needle-in-a-Haystack lack complexity. In this work, we argue that summarization can play a central role in such evaluation. We design a procedure to synthesize Haystacks of documents, ensuring that specific \\textit{insights} repeat across documents. The \"Summary of a Haystack\" (SummHay) task then requires a system to process the Haystack and generate, given a query, a summary that identifies the releva","authors_text":"Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu, Philippe Laban","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T15:23:42Z","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01370","kind":"arxiv","version":1},"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":"sha256:85f9467eb827fca7c307b69fb416cadba040b2781dfc30ca7a94abbdb1ee7389","target":"record","created_at":"2026-07-05T08:38:47Z","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":"9690f768aeec36ea99c7c01bc6fa67e2c5a5ca94899e6afefaded378f35a705e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T15:23:42Z","title_canon_sha256":"332786d0c99b2150b26ce4db55f2c03eb4863c926d56096f7485cded9fc9ff41"},"schema_version":"1.0","source":{"id":"2407.01370","kind":"arxiv","version":1}},"canonical_sha256":"6935aa57b9e2f6ec9c60c98ca6c31df333b5df4b5c802b41ab2f3e622224ab1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6935aa57b9e2f6ec9c60c98ca6c31df333b5df4b5c802b41ab2f3e622224ab1a","first_computed_at":"2026-07-05T08:38:47.073439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:47.073439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TsDEw2try6ml8wOKbdxnR1OmLpsS+2VpAU24oZCuJVFoEVcWRMYvJSL2BwD6bT/bdobYoc00KZYpwI04ZE8qDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:47.074056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85f9467eb827fca7c307b69fb416cadba040b2781dfc30ca7a94abbdb1ee7389","sha256:dd1437b556aacccfb72e7bbf6dc5bd6660c98adf44f949ab163705372b7e8f51"],"state_sha256":"107648d6d29991510516b57d63a7cd6525e6f8306c29861fac448c200bee61a7"}