{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LFK7AV3JWHISWM3KGVPUXWFZ6J","short_pith_number":"pith:LFK7AV3J","schema_version":"1.0","canonical_sha256":"5955f05769b1d12b336a355f4bd8b9f2647152236494b765cc4555eb0f8f6996","source":{"kind":"arxiv","id":"2601.03014","version":3},"attestation_state":"computed","paper":{"title":"SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junli Liang, Pengfei Zhou, Qi Song, Qi Zhao, Wangqiu Zhou, Wenjie Qing, Xiangyang Li, Ziwen Wang","submitted_at":"2026-01-06T13:39:51Z","abstract_excerpt":"Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from multiple documents. Existing chunk-based retrieval often provides irrelevant and logically incoherent context, leading to incomplete evidence chains and incorrect reasoning during answer generation. To address these challenges, we propose SentGraph, a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sen"},"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":"2601.03014","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T13:39:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"818a4092fcbe7d3ecf77e159bb623a7f7259a5633e6ddfbd9c54ab08d3061271","abstract_canon_sha256":"9105cf32a7c653d4a2c5f29a02b381e42cc92e03a0b821d959f647e60ce0ea91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:21.799561Z","signature_b64":"6Wzc1uaFKw+/OSTTZPpPvE57oEdKB5HK8ndTMaoGG6xkWSDJ3tG33Chb3nyTFwBptUugyYxHZ4t5juiDJziEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5955f05769b1d12b336a355f4bd8b9f2647152236494b765cc4555eb0f8f6996","last_reissued_at":"2026-05-26T01:03:21.798651Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:21.798651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junli Liang, Pengfei Zhou, Qi Song, Qi Zhao, Wangqiu Zhou, Wenjie Qing, Xiangyang Li, Ziwen Wang","submitted_at":"2026-01-06T13:39:51Z","abstract_excerpt":"Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from multiple documents. Existing chunk-based retrieval often provides irrelevant and logically incoherent context, leading to incomplete evidence chains and incorrect reasoning during answer generation. To address these challenges, we propose SentGraph, a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03014","kind":"arxiv","version":3},"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/2601.03014/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":"2601.03014","created_at":"2026-05-26T01:03:21.798782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03014v3","created_at":"2026-05-26T01:03:21.798782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03014","created_at":"2026-05-26T01:03:21.798782+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFK7AV3JWHIS","created_at":"2026-05-26T01:03:21.798782+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFK7AV3JWHISWM3K","created_at":"2026-05-26T01:03:21.798782+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFK7AV3J","created_at":"2026-05-26T01:03:21.798782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.10516","citing_title":"Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J","json":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J.json","graph_json":"https://pith.science/api/pith-number/LFK7AV3JWHISWM3KGVPUXWFZ6J/graph.json","events_json":"https://pith.science/api/pith-number/LFK7AV3JWHISWM3KGVPUXWFZ6J/events.json","paper":"https://pith.science/paper/LFK7AV3J"},"agent_actions":{"view_html":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J","download_json":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J.json","view_paper":"https://pith.science/paper/LFK7AV3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03014&json=true","fetch_graph":"https://pith.science/api/pith-number/LFK7AV3JWHISWM3KGVPUXWFZ6J/graph.json","fetch_events":"https://pith.science/api/pith-number/LFK7AV3JWHISWM3KGVPUXWFZ6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J/action/storage_attestation","attest_author":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J/action/author_attestation","sign_citation":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J/action/citation_signature","submit_replication":"https://pith.science/pith/LFK7AV3JWHISWM3KGVPUXWFZ6J/action/replication_record"}},"created_at":"2026-05-26T01:03:21.798782+00:00","updated_at":"2026-05-26T01:03:21.798782+00:00"}