{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RGJ3BUUMI3VMZM5UKCUBM5O4BE","short_pith_number":"pith:RGJ3BUUM","schema_version":"1.0","canonical_sha256":"8993b0d28c46eaccb3b450a81675dc093beba03200026f245911bce54ff226e0","source":{"kind":"arxiv","id":"2312.17269","version":2},"attestation_state":"computed","paper":{"title":"Conversational Question Answering with Reformulations over Knowledge Graph","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Blaine Hill, Boxin Du, Fei Wang, Hanghang Tong, Lihui Liu","submitted_at":"2023-12-27T00:03:05Z","abstract_excerpt":"Conversational question answering (convQA) over knowledge graphs (KGs) involves answering multi-turn natural language questions about information contained in a KG. State-of-the-art methods of ConvQA often struggle with inexplicit question-answer pairs. These inputs are easy for human beings to understand given a conversation history, but hard for a machine to interpret, which can degrade ConvQA performance. To address this problem, we propose a reinforcement learning (RL) based model, CornNet, which utilizes question reformulations generated by large language models (LLMs) to improve ConvQA p"},"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":"2312.17269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-27T00:03:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0570366be89845344ec61ab2da7bd18f6cd41b342d1a76e2cdd0e4e01a1353f7","abstract_canon_sha256":"8c2d69188a7e5d5a73eae198ea523ba54df6fa21181c67c348ed1fb3ee7f7ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:04.023224Z","signature_b64":"Ar9aXLKHWjdwhDyexIFOyylIFYUo6PFLnIHM7QXPFzdQtSPB7rRbZo0EGn4LD/PC2sCgB9TkFNNCOAwoHcVDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8993b0d28c46eaccb3b450a81675dc093beba03200026f245911bce54ff226e0","last_reissued_at":"2026-07-05T08:02:04.022786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:04.022786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conversational Question Answering with Reformulations over Knowledge Graph","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Blaine Hill, Boxin Du, Fei Wang, Hanghang Tong, Lihui Liu","submitted_at":"2023-12-27T00:03:05Z","abstract_excerpt":"Conversational question answering (convQA) over knowledge graphs (KGs) involves answering multi-turn natural language questions about information contained in a KG. State-of-the-art methods of ConvQA often struggle with inexplicit question-answer pairs. These inputs are easy for human beings to understand given a conversation history, but hard for a machine to interpret, which can degrade ConvQA performance. To address this problem, we propose a reinforcement learning (RL) based model, CornNet, which utilizes question reformulations generated by large language models (LLMs) to improve ConvQA p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17269","kind":"arxiv","version":2},"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/2312.17269/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":"2312.17269","created_at":"2026-07-05T08:02:04.022843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17269v2","created_at":"2026-07-05T08:02:04.022843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17269","created_at":"2026-07-05T08:02:04.022843+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGJ3BUUMI3VM","created_at":"2026-07-05T08:02:04.022843+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGJ3BUUMI3VMZM5U","created_at":"2026-07-05T08:02:04.022843+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGJ3BUUM","created_at":"2026-07-05T08:02:04.022843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE","json":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE.json","graph_json":"https://pith.science/api/pith-number/RGJ3BUUMI3VMZM5UKCUBM5O4BE/graph.json","events_json":"https://pith.science/api/pith-number/RGJ3BUUMI3VMZM5UKCUBM5O4BE/events.json","paper":"https://pith.science/paper/RGJ3BUUM"},"agent_actions":{"view_html":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE","download_json":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE.json","view_paper":"https://pith.science/paper/RGJ3BUUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17269&json=true","fetch_graph":"https://pith.science/api/pith-number/RGJ3BUUMI3VMZM5UKCUBM5O4BE/graph.json","fetch_events":"https://pith.science/api/pith-number/RGJ3BUUMI3VMZM5UKCUBM5O4BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE/action/storage_attestation","attest_author":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE/action/author_attestation","sign_citation":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE/action/citation_signature","submit_replication":"https://pith.science/pith/RGJ3BUUMI3VMZM5UKCUBM5O4BE/action/replication_record"}},"created_at":"2026-07-05T08:02:04.022843+00:00","updated_at":"2026-07-05T08:02:04.022843+00:00"}