{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH","short_pith_number":"pith:AJ5RA3L2","schema_version":"1.0","canonical_sha256":"027b106d7aabcc57247ecc3d90854b81d091e64898239941fc9046b9c074de52","source":{"kind":"arxiv","id":"2607.01852","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreas Fischer, Johannes Reisinger, Valentin J. J. Kreileder","submitted_at":"2026-07-02T08:12:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters. We evaluate if cluster-based semantic chunking improves retrieval and answer quality compared to fixed-size and recursive chunking evaluating on long, structured academic theses using the Retrieval Augmented Generation Assessment (RAGAs) framework. RAGAs based faithfulness shows limited reliability in this setup. Performance on fixed versus document specific questions varied substantially, likely related to the formatting of docume"},"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":"2607.01852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-02T08:12:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"48ad4fd8550a3ca28d5c3e0d838bad608c97bee4ec665326427635ce26d8e8f1","abstract_canon_sha256":"ebbddc20f8f770e52a489b41db7400df11134376f5e47055cb5ed79505f3b620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:31.678778Z","signature_b64":"e2O3Pkydqcdpg+Zs4El0t+/G3fv7sK0ndLmxM05JHJxl1FaJ4tNb8uyf8NbEfZorqAJbwNQwW9LNCbcO31imCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027b106d7aabcc57247ecc3d90854b81d091e64898239941fc9046b9c074de52","last_reissued_at":"2026-07-03T01:17:31.678396Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:31.678396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreas Fischer, Johannes Reisinger, Valentin J. J. Kreileder","submitted_at":"2026-07-02T08:12:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters. We evaluate if cluster-based semantic chunking improves retrieval and answer quality compared to fixed-size and recursive chunking evaluating on long, structured academic theses using the Retrieval Augmented Generation Assessment (RAGAs) framework. RAGAs based faithfulness shows limited reliability in this setup. Performance on fixed versus document specific questions varied substantially, likely related to the formatting of docume"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01852","kind":"arxiv","version":1},"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/2607.01852/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":"2607.01852","created_at":"2026-07-03T01:17:31.678462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01852v1","created_at":"2026-07-03T01:17:31.678462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01852","created_at":"2026-07-03T01:17:31.678462+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ5RA3L2VPGF","created_at":"2026-07-03T01:17:31.678462+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ5RA3L2VPGFOJD6","created_at":"2026-07-03T01:17:31.678462+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ5RA3L2","created_at":"2026-07-03T01:17:31.678462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH","json":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH.json","graph_json":"https://pith.science/api/pith-number/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/graph.json","events_json":"https://pith.science/api/pith-number/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/events.json","paper":"https://pith.science/paper/AJ5RA3L2"},"agent_actions":{"view_html":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH","download_json":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH.json","view_paper":"https://pith.science/paper/AJ5RA3L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01852&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/action/storage_attestation","attest_author":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/action/author_attestation","sign_citation":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/action/citation_signature","submit_replication":"https://pith.science/pith/AJ5RA3L2VPGFOJD6ZQ6ZBBKLQH/action/replication_record"}},"created_at":"2026-07-03T01:17:31.678462+00:00","updated_at":"2026-07-03T01:17:31.678462+00:00"}