{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DK2NH3SFEC5QFIW7Z6IWPQW2ZW","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":"1c2a076b1841c402104782e384e178c78b93e511b2dfebc0e3b751769b9567c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T12:09:03Z","title_canon_sha256":"284ea26990eea2b65fb78060147ea18c2ec44eb44bd90f966ef66acb0dabb7b7"},"schema_version":"1.0","source":{"id":"2607.24332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24332","created_at":"2026-07-28T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24332v1","created_at":"2026-07-28T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24332","created_at":"2026-07-28T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"DK2NH3SFEC5Q","created_at":"2026-07-28T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"DK2NH3SFEC5QFIW7","created_at":"2026-07-28T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"DK2NH3SF","created_at":"2026-07-28T02:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:9aa88d8a70b57600d0bf13f1b1326392a6c4c427da686279a291594b56c185f6","target":"graph","created_at":"2026-07-28T02:23:57Z","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/2607.24332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common chunking strategies in Retrieval-Augmented Generation (RAG) systems often create redundant chunks. These redundant chunks make the vector database bigger and slow down retrieval. A common fix is cosine-similarity thresholding. This method reduces each chunk to a single vector, then compares vectors using a similarity score. But a single vector can lose the fine-grained, token-level detail needed to tell a true duplicate apart from a chunk that just shares the same topic. We propose Cross-Attention Calibrated Deduplication (CACD). CACD checks each new chunk against an in-memory pool of c","authors_text":"Nam H. Nguyen, Phuong Le Huy, Quan V. Dang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T12:09:03Z","title":"Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24332","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:f2c68bfca0cefce8245950d0e212afd627d5387ac7df3de15d2ef96b7e007a67","target":"record","created_at":"2026-07-28T02:23:57Z","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":"1c2a076b1841c402104782e384e178c78b93e511b2dfebc0e3b751769b9567c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T12:09:03Z","title_canon_sha256":"284ea26990eea2b65fb78060147ea18c2ec44eb44bd90f966ef66acb0dabb7b7"},"schema_version":"1.0","source":{"id":"2607.24332","kind":"arxiv","version":1}},"canonical_sha256":"1ab4d3ee4520bb02a2dfcf9167c2dacdb945d70bdc592872e969194387068217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ab4d3ee4520bb02a2dfcf9167c2dacdb945d70bdc592872e969194387068217","first_computed_at":"2026-07-28T02:23:57.737040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:57.737040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxtOgbfCdmKxzrCyMYFoUIkeBO78ajG5z5vFZOTc3n7lyOQH4fpL/iUXWgAbkdn77Yzq7pw7mdLYNX6hLf+YCw==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:57.737942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2c68bfca0cefce8245950d0e212afd627d5387ac7df3de15d2ef96b7e007a67","sha256:9aa88d8a70b57600d0bf13f1b1326392a6c4c427da686279a291594b56c185f6"],"state_sha256":"a3f3c4999639904ac90bbb5d1173ed055318498c97f892ff08f07ab5c36a65a8"}