{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QPLL27O4HTWQKT7GUC6XHEHT2W","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":"813f2eaaebd1a8055234ccd05ad4557b8c738eb45e522877873ca79892ab8bff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T19:39:16Z","title_canon_sha256":"1cd09f5744bf1fbe938836d42f24b1832031889bd1ee2e47f0cf61f73ad47399"},"schema_version":"1.0","source":{"id":"2505.21700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21700","created_at":"2026-07-05T11:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21700v2","created_at":"2026-07-05T11:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21700","created_at":"2026-07-05T11:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"QPLL27O4HTWQ","created_at":"2026-07-05T11:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"QPLL27O4HTWQKT7G","created_at":"2026-07-05T11:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"QPLL27O4","created_at":"2026-07-05T11:11:47Z"}],"graph_snapshots":[{"event_id":"sha256:d75d37f09ac4fbb872e98dbf8280ef804807a9493efc2f50580ffa53b94dc2f1","target":"graph","created_at":"2026-07-05T11:11:47Z","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/2505.21700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and their influence on retrieval performance using multiple embedding models. Our experiments, conducted on both short-form and long-form datasets, reveal that chunk size plays a critical role in retrieval effectiveness -- smaller chunks (64-128 tokens) are optimal for datasets with concise, fact-based answers, whereas larger chunks (512-1024 tokens) improve ret","authors_text":"Jannis Spiekermann, Max Rudat, Nicolas Flores-Herr, Sinchana Ramakanth Bhat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T19:39:16Z","title":"Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21700","kind":"arxiv","version":2},"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:e44770a138019bd135c394b2cb42ce64d3a07b74ed2d0b11ba5a4afea7954a47","target":"record","created_at":"2026-07-05T11:11:47Z","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":"813f2eaaebd1a8055234ccd05ad4557b8c738eb45e522877873ca79892ab8bff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T19:39:16Z","title_canon_sha256":"1cd09f5744bf1fbe938836d42f24b1832031889bd1ee2e47f0cf61f73ad47399"},"schema_version":"1.0","source":{"id":"2505.21700","kind":"arxiv","version":2}},"canonical_sha256":"83d6bd7ddc3ced054fe6a0bd7390f3d59ec54213c8d52c13c3fed0a9d6567c88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83d6bd7ddc3ced054fe6a0bd7390f3d59ec54213c8d52c13c3fed0a9d6567c88","first_computed_at":"2026-07-05T11:11:47.330898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:47.330898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"un8sXGe5JimEM9gjXY/bQc8qFwzE0IR7orBEMGEqVFXYyzdT4uNsfSnnYRxOQVbPlAIY0HgobMTlHS05pKFaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:47.331490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e44770a138019bd135c394b2cb42ce64d3a07b74ed2d0b11ba5a4afea7954a47","sha256:d75d37f09ac4fbb872e98dbf8280ef804807a9493efc2f50580ffa53b94dc2f1"],"state_sha256":"25d61a45738da839dcc1fe3a84552cc3c35c592efa12ec2fd88b7512e1e0a668"}