{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WZEFTHBYA3TNIQ7OAGNE5TTJJQ","short_pith_number":"pith:WZEFTHBY","canonical_record":{"source":{"id":"2509.00449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T10:44:06Z","cross_cats_sorted":[],"title_canon_sha256":"20cc90114cb25f07e3ff25a9322b834749134f0c97f7fbecc24ea95f869740a3","abstract_canon_sha256":"64de1038d0dbc9b77546a1ff2d9ee1ade5ad7d554d7d2248c8cd42d7f3d87850"},"schema_version":"1.0"},"canonical_sha256":"b648599c3806e6d443ee019a4ece694c0e36b506c31d3143445da0e02d346b39","source":{"kind":"arxiv","id":"2509.00449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00449","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00449v1","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00449","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"WZEFTHBYA3TN","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"WZEFTHBYA3TNIQ7O","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"WZEFTHBY","created_at":"2026-07-05T12:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WZEFTHBYA3TNIQ7OAGNE5TTJJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T10:44:06Z","cross_cats_sorted":[],"title_canon_sha256":"20cc90114cb25f07e3ff25a9322b834749134f0c97f7fbecc24ea95f869740a3","abstract_canon_sha256":"64de1038d0dbc9b77546a1ff2d9ee1ade5ad7d554d7d2248c8cd42d7f3d87850"},"schema_version":"1.0"},"canonical_sha256":"b648599c3806e6d443ee019a4ece694c0e36b506c31d3143445da0e02d346b39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:16.528864Z","signature_b64":"ZMt9xCl3hnFmZ2n7lpupfwyD1fHSJIEQKTTSNHII1iuZ/MeUpTDpz2tSGjH4GU2Ur6AyL9OhPr0jGlyZ4XOfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b648599c3806e6d443ee019a4ece694c0e36b506c31d3143445da0e02d346b39","last_reissued_at":"2026-07-05T12:02:16.528346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:16.528346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00449","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0H78mh/rX21HxPCCxX1fnrz1WnAlENInV3TPV/eQWxjQtMPqKgFON7eFW2K0dRo/lXqRv4F5qUMx53mqpwaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:31:18.285990Z"},"content_sha256":"3d9a4d5953db75ff8dc148389b626a03f75e94c1cdd1178c7bd420e516a1e270","schema_version":"1.0","event_id":"sha256:3d9a4d5953db75ff8dc148389b626a03f75e94c1cdd1178c7bd420e516a1e270"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WZEFTHBYA3TNIQ7OAGNE5TTJJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingbing Wang, Huafei Deng, Ke Liu, Li Zhang, Xuecheng Zou, Yu Tang","submitted_at":"2025-08-30T10:44:06Z","abstract_excerpt":"Building upon the standard graph-based Retrieval-Augmented Generation (RAG), the introduction of heterogeneous graphs and hypergraphs aims to enrich retrieval and generation by leveraging the relationships between multiple entities through the concept of semantic units (SUs). But this also raises a key issue: The extraction of high-level SUs limited to local text chunks is prone to ambiguity, complex coupling, and increased retrieval overhead due to the lack of global knowledge or the neglect of fine-grained relationships. To address these issues, we propose GOSU, a semantic unit-centric RAG f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00449","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/2509.00449/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDjRjfiZC3jOz73Z0Cu2Rpr0IgjVtq3u5l939VIPCnG9EY51ahNAj+dPA3rK7XuFtYC9IAfi+Cs3jW3whQ5GBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:31:18.286573Z"},"content_sha256":"1f4d4e67f2ebddc21afcd8a2753ea7666a753ec3d30b88cafdce537bfdcd5885","schema_version":"1.0","event_id":"sha256:1f4d4e67f2ebddc21afcd8a2753ea7666a753ec3d30b88cafdce537bfdcd5885"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/bundle.json","state_url":"https://pith.science/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T23:31:18Z","links":{"resolver":"https://pith.science/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ","bundle":"https://pith.science/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/bundle.json","state":"https://pith.science/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZEFTHBYA3TNIQ7OAGNE5TTJJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WZEFTHBYA3TNIQ7OAGNE5TTJJQ","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":"64de1038d0dbc9b77546a1ff2d9ee1ade5ad7d554d7d2248c8cd42d7f3d87850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T10:44:06Z","title_canon_sha256":"20cc90114cb25f07e3ff25a9322b834749134f0c97f7fbecc24ea95f869740a3"},"schema_version":"1.0","source":{"id":"2509.00449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00449","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00449v1","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00449","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"WZEFTHBYA3TN","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"WZEFTHBYA3TNIQ7O","created_at":"2026-07-05T12:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"WZEFTHBY","created_at":"2026-07-05T12:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:1f4d4e67f2ebddc21afcd8a2753ea7666a753ec3d30b88cafdce537bfdcd5885","target":"graph","created_at":"2026-07-05T12:02:16Z","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/2509.00449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building upon the standard graph-based Retrieval-Augmented Generation (RAG), the introduction of heterogeneous graphs and hypergraphs aims to enrich retrieval and generation by leveraging the relationships between multiple entities through the concept of semantic units (SUs). But this also raises a key issue: The extraction of high-level SUs limited to local text chunks is prone to ambiguity, complex coupling, and increased retrieval overhead due to the lack of global knowledge or the neglect of fine-grained relationships. To address these issues, we propose GOSU, a semantic unit-centric RAG f","authors_text":"Bingbing Wang, Huafei Deng, Ke Liu, Li Zhang, Xuecheng Zou, Yu Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T10:44:06Z","title":"GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00449","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":"sha256:3d9a4d5953db75ff8dc148389b626a03f75e94c1cdd1178c7bd420e516a1e270","target":"record","created_at":"2026-07-05T12:02:16Z","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":"64de1038d0dbc9b77546a1ff2d9ee1ade5ad7d554d7d2248c8cd42d7f3d87850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T10:44:06Z","title_canon_sha256":"20cc90114cb25f07e3ff25a9322b834749134f0c97f7fbecc24ea95f869740a3"},"schema_version":"1.0","source":{"id":"2509.00449","kind":"arxiv","version":1}},"canonical_sha256":"b648599c3806e6d443ee019a4ece694c0e36b506c31d3143445da0e02d346b39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b648599c3806e6d443ee019a4ece694c0e36b506c31d3143445da0e02d346b39","first_computed_at":"2026-07-05T12:02:16.528346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:16.528346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZMt9xCl3hnFmZ2n7lpupfwyD1fHSJIEQKTTSNHII1iuZ/MeUpTDpz2tSGjH4GU2Ur6AyL9OhPr0jGlyZ4XOfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:16.528864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d9a4d5953db75ff8dc148389b626a03f75e94c1cdd1178c7bd420e516a1e270","sha256:1f4d4e67f2ebddc21afcd8a2753ea7666a753ec3d30b88cafdce537bfdcd5885"],"state_sha256":"a58bab2c1ef618de7bf1ba413a7153608e205738caff1eab36143a127e9432e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SgzPSvhIpeTTm8sVadsKj/GDBRmRD2CnkzECc63RNBBW5VJEmXZrxtOeRii77NPSaIBYRwZN2Gq5tUsm1/hCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:31:18.290274Z","bundle_sha256":"75308eb1e2525a5a21ad178bdefe7701e9606cd3ccbdc2bdbf56c4009fafd1ce"}}