{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NI2OKBAFJINEWEHD6ECGFL6CGF","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":"5d0fe186335200335d637094ff772caae120372d68bcaf5c79ddbb06b3dfea0b","cross_cats_sorted":["cs.AI","physics.chem-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-13T07:44:53Z","title_canon_sha256":"30fb06b4614138158332377eaa48fce370ead0698a9b26975e6150328ec7a597"},"schema_version":"1.0","source":{"id":"2506.17277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17277","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17277v1","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17277","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"NI2OKBAFJINE","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"NI2OKBAFJINEWEHD","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"NI2OKBAF","created_at":"2026-07-05T11:25:14Z"}],"graph_snapshots":[{"event_id":"sha256:a378d0abf715486cae4dabd0aae64d5d15deb26a8d9525339ee92aac9628118a","target":"graph","created_at":"2026-07-05T11:25:14Z","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/2506.17277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design choices -- such as how documents are segmented and represented -- remain underexplored in domain-specific contexts. This study presents the first large-scale, systematic evaluation of chunking strategies and embedding models tailored to chemistry-focused RAG systems. We investigate 25 chunking configurations across five method families and evaluate 48 embedding ","authors_text":"Mahmoud Amiri, Thomas Bocklitz","cross_cats":["cs.AI","physics.chem-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-13T07:44:53Z","title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17277","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":"sha256:2130be5cc6ef5893ee63902225b7f168ece743326916b14a5edd9fbfe4fa1c91","target":"record","created_at":"2026-07-05T11:25:14Z","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":"5d0fe186335200335d637094ff772caae120372d68bcaf5c79ddbb06b3dfea0b","cross_cats_sorted":["cs.AI","physics.chem-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-13T07:44:53Z","title_canon_sha256":"30fb06b4614138158332377eaa48fce370ead0698a9b26975e6150328ec7a597"},"schema_version":"1.0","source":{"id":"2506.17277","kind":"arxiv","version":1}},"canonical_sha256":"6a34e504054a1a4b10e3f10462afc2317993c49dcdb41b7513311aebcb254649","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a34e504054a1a4b10e3f10462afc2317993c49dcdb41b7513311aebcb254649","first_computed_at":"2026-07-05T11:25:14.686304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:14.686304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0DsvK+RkhGVoJDC+ysXy792HsRkqIgqlo2s0k5zIgu5vUHeBvR7N4fj4hjIkEWBZtabcpdgn3Lz3ryf1EJg4Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:14.686794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2130be5cc6ef5893ee63902225b7f168ece743326916b14a5edd9fbfe4fa1c91","sha256:a378d0abf715486cae4dabd0aae64d5d15deb26a8d9525339ee92aac9628118a"],"state_sha256":"a3ce3fd6377689dd62309919df251909d63d020d5d38b8eeba90a60930d15af6"}