{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JW37OIQFEURLFWIVEDSKTTQPCE","short_pith_number":"pith:JW37OIQF","schema_version":"1.0","canonical_sha256":"4db7f722052522b2d91520e4a9ce0f112bc457a7df9cec4eb0cf2ae8e0fb6837","source":{"kind":"arxiv","id":"2509.03995","version":1},"attestation_state":"computed","paper":{"title":"RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huajun Chen, Juan Li, Lei Liang, Wen Zhang, Zhaoyan Gong, Zhiqiang Liu","submitted_at":"2025-09-04T08:25:01Z","abstract_excerpt":"Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves them bottom-up using LLMs and TKG knowledge, and employs multi-path answer aggregation to improve fau"},"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":"2509.03995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T08:25:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a64cfcf297fcd5a45cc3e9521f30f6925abc68be04973d554f2b8bb015d7578b","abstract_canon_sha256":"dc38d8b9905488395cd26c2aae2361562bac345f4dc89e70d522085d4e89fa27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:51.396890Z","signature_b64":"lub8JU6jbhy9XqkToscvhlUxDHzA4V4UzAuwWEHIPGEDh8BKKn1NxECz+cPyLJVX5ybIL8T1jnbQXz2yM5PcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db7f722052522b2d91520e4a9ce0f112bc457a7df9cec4eb0cf2ae8e0fb6837","last_reissued_at":"2026-07-05T12:04:51.396379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:51.396379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huajun Chen, Juan Li, Lei Liang, Wen Zhang, Zhaoyan Gong, Zhiqiang Liu","submitted_at":"2025-09-04T08:25:01Z","abstract_excerpt":"Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves them bottom-up using LLMs and TKG knowledge, and employs multi-path answer aggregation to improve fau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03995","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/2509.03995/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":"2509.03995","created_at":"2026-07-05T12:04:51.396441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03995v1","created_at":"2026-07-05T12:04:51.396441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03995","created_at":"2026-07-05T12:04:51.396441+00:00"},{"alias_kind":"pith_short_12","alias_value":"JW37OIQFEURL","created_at":"2026-07-05T12:04:51.396441+00:00"},{"alias_kind":"pith_short_16","alias_value":"JW37OIQFEURLFWIV","created_at":"2026-07-05T12:04:51.396441+00:00"},{"alias_kind":"pith_short_8","alias_value":"JW37OIQF","created_at":"2026-07-05T12:04:51.396441+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/JW37OIQFEURLFWIVEDSKTTQPCE","json":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE.json","graph_json":"https://pith.science/api/pith-number/JW37OIQFEURLFWIVEDSKTTQPCE/graph.json","events_json":"https://pith.science/api/pith-number/JW37OIQFEURLFWIVEDSKTTQPCE/events.json","paper":"https://pith.science/paper/JW37OIQF"},"agent_actions":{"view_html":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE","download_json":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE.json","view_paper":"https://pith.science/paper/JW37OIQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03995&json=true","fetch_graph":"https://pith.science/api/pith-number/JW37OIQFEURLFWIVEDSKTTQPCE/graph.json","fetch_events":"https://pith.science/api/pith-number/JW37OIQFEURLFWIVEDSKTTQPCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE/action/storage_attestation","attest_author":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE/action/author_attestation","sign_citation":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE/action/citation_signature","submit_replication":"https://pith.science/pith/JW37OIQFEURLFWIVEDSKTTQPCE/action/replication_record"}},"created_at":"2026-07-05T12:04:51.396441+00:00","updated_at":"2026-07-05T12:04:51.396441+00:00"}