{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:42BTHFBO6733UOG5GGERTRYEDT","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":"2c37fcac6caa56b6177af9c68f1d365c245853792da85a68903d754a17a7dec1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-06T11:37:10Z","title_canon_sha256":"ac3dff5b864ed7943b3b8ce6fc1fde67b916e92266c42eda96eea0b7fa6115d4"},"schema_version":"1.0","source":{"id":"2603.29875","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29875","created_at":"2026-06-09T02:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29875v3","created_at":"2026-06-09T02:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29875","created_at":"2026-06-09T02:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"42BTHFBO6733","created_at":"2026-06-09T02:07:25Z"},{"alias_kind":"pith_short_16","alias_value":"42BTHFBO6733UOG5","created_at":"2026-06-09T02:07:25Z"},{"alias_kind":"pith_short_8","alias_value":"42BTHFBO","created_at":"2026-06-09T02:07:25Z"}],"graph_snapshots":[{"event_id":"sha256:3c925ba914dca4f32eedb8e7e467f0d9b7b24f4a18662a1e201b690c646e1258","target":"graph","created_at":"2026-06-09T02:07:25Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That an LLM can reliably extract entities across chunks without introducing systematic errors or hallucinations that would then propagate into retrieval."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UnWeaver disentangles documents into entities via LLM to retrieve original chunks, yielding a simpler alternative to GraphRAG that still reduces noise and preserves source fidelity."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Entity decomposition of documents into cross-chunk links simplifies GraphRAG to near VectorRAG performance while preserving source fidelity."}],"snapshot_sha256":"e69e2cb58a4dfb425287868efb97ee519c9ca3a33afcde481042e17660201771"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.29875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector. These vector representations are then fundamentally treated as isolated, independent and self-sufficient, with no attempt to represent possible relations between them. Such an approach has no dedicated mechanisms for handling multi-hop questions. Graph-based RAG systems aimed to ameliorate this problem by modeling information as knowledge-graphs, with entities rep","authors_text":"Adam Kozakiewicz, Mateusz Czy\\.znikiewicz, Mateusz Gali\\'nski, Micha{\\l} Godziszewski, Micha{\\l} Karpowicz, Ryszard Tuora, Tomasz Zi\\k{e}tkiewicz","cross_cats":["cs.AI","cs.CL"],"headline":"Entity decomposition of documents into cross-chunk links simplifies GraphRAG to near VectorRAG performance while preserving source fidelity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-06T11:37:10Z","title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29875","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T06:55:43.692655Z","id":"80cf293e-fb16-4d78-9158-a82097b3509b","model_set":{"reader":"grok-4.3"},"one_line_summary":"UnWeaver disentangles documents into entities via LLM to retrieve original chunks, yielding a simpler alternative to GraphRAG that still reduces noise and preserves source fidelity.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Entity decomposition of documents into cross-chunk links simplifies GraphRAG to near VectorRAG performance while preserving source fidelity.","strongest_claim":"entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process.","weakest_assumption":"That an LLM can reliably extract entities across chunks without introducing systematic errors or hallucinations that would then propagate into retrieval."}},"verdict_id":"80cf293e-fb16-4d78-9158-a82097b3509b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ae0632e96f5a99fdfe0bc71798ead83e406b195c7460048d357a412ed22f908","target":"record","created_at":"2026-06-09T02:07:25Z","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":"2c37fcac6caa56b6177af9c68f1d365c245853792da85a68903d754a17a7dec1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-06T11:37:10Z","title_canon_sha256":"ac3dff5b864ed7943b3b8ce6fc1fde67b916e92266c42eda96eea0b7fa6115d4"},"schema_version":"1.0","source":{"id":"2603.29875","kind":"arxiv","version":3}},"canonical_sha256":"e68333942ef7f7ba38dd318919c7041cc5300b9c6c5189388e97c7cf73a1d617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e68333942ef7f7ba38dd318919c7041cc5300b9c6c5189388e97c7cf73a1d617","first_computed_at":"2026-06-09T02:07:25.722438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:25.722438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JKGv0jxsMY6i4uVe8hUpZIBuDr5xKojGDBvBJk/E5ZabmI7mumRylJiVCG57bTa/uIs+jpz80hRafo57HtPpAA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:25.723582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29875","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ae0632e96f5a99fdfe0bc71798ead83e406b195c7460048d357a412ed22f908","sha256:3c925ba914dca4f32eedb8e7e467f0d9b7b24f4a18662a1e201b690c646e1258"],"state_sha256":"21eb739553d0d4e0774c8586452614ba09eff16f6e316a124b353a9b03dec26a"}