{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OMZ6G44TMFMDS3U44DYRG6M5CW","short_pith_number":"pith:OMZ6G44T","schema_version":"1.0","canonical_sha256":"7333e373936158396e9ce0f113799d15876d84ae58c3cfe48d3de303df3e7d29","source":{"kind":"arxiv","id":"2412.05453","version":3},"attestation_state":"computed","paper":{"title":"Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinash Anand, Chhavi Kirtani, Dhruv Jain, Kabir Dev Paul Baghel, Krishnasai Addala, Navya Gupta, Rajiv Ratn Shah, Rishitej Reddy Vyalla","submitted_at":"2024-12-06T22:25:23Z","abstract_excerpt":"This study explores the effectiveness of using knowledge graphs generated by large language models to decompose high school-level physics questions into sub-questions. We introduce a pipeline aimed at enhancing model response quality for Question Answering tasks. By employing LLMs to construct knowledge graphs that capture the internal logic of the questions, these graphs then guide the generation of subquestions. We hypothesize that this method yields sub-questions that are more logically consistent with the original questions compared to traditional decomposition techniques. Our results show"},"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":"2412.05453","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T22:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"7b1ad2d51bd6e3a4ec8c41b41ca08a540f864187a7fcb5152ac26b764dd200f6","abstract_canon_sha256":"3db81f2532ec93bc9b2156808072947b846c40d84504c7098b7d37edc73ee21f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:50.276536Z","signature_b64":"dyYJmUOKirOiCxJF/eud5oIG3a6BRD4Kw/4yERGsYlOVCCUj7b39caR+irTT62mIfIeV81WYeagx3pDVi+CjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7333e373936158396e9ce0f113799d15876d84ae58c3cfe48d3de303df3e7d29","last_reissued_at":"2026-07-05T11:19:50.276050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:50.276050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinash Anand, Chhavi Kirtani, Dhruv Jain, Kabir Dev Paul Baghel, Krishnasai Addala, Navya Gupta, Rajiv Ratn Shah, Rishitej Reddy Vyalla","submitted_at":"2024-12-06T22:25:23Z","abstract_excerpt":"This study explores the effectiveness of using knowledge graphs generated by large language models to decompose high school-level physics questions into sub-questions. We introduce a pipeline aimed at enhancing model response quality for Question Answering tasks. By employing LLMs to construct knowledge graphs that capture the internal logic of the questions, these graphs then guide the generation of subquestions. We hypothesize that this method yields sub-questions that are more logically consistent with the original questions compared to traditional decomposition techniques. Our results show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05453","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/2412.05453/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":"2412.05453","created_at":"2026-07-05T11:19:50.276108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05453v3","created_at":"2026-07-05T11:19:50.276108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05453","created_at":"2026-07-05T11:19:50.276108+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMZ6G44TMFMD","created_at":"2026-07-05T11:19:50.276108+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMZ6G44TMFMDS3U4","created_at":"2026-07-05T11:19:50.276108+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMZ6G44T","created_at":"2026-07-05T11:19:50.276108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04978","citing_title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","ref_index":138,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW","json":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW.json","graph_json":"https://pith.science/api/pith-number/OMZ6G44TMFMDS3U44DYRG6M5CW/graph.json","events_json":"https://pith.science/api/pith-number/OMZ6G44TMFMDS3U44DYRG6M5CW/events.json","paper":"https://pith.science/paper/OMZ6G44T"},"agent_actions":{"view_html":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW","download_json":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW.json","view_paper":"https://pith.science/paper/OMZ6G44T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05453&json=true","fetch_graph":"https://pith.science/api/pith-number/OMZ6G44TMFMDS3U44DYRG6M5CW/graph.json","fetch_events":"https://pith.science/api/pith-number/OMZ6G44TMFMDS3U44DYRG6M5CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW/action/storage_attestation","attest_author":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW/action/author_attestation","sign_citation":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW/action/citation_signature","submit_replication":"https://pith.science/pith/OMZ6G44TMFMDS3U44DYRG6M5CW/action/replication_record"}},"created_at":"2026-07-05T11:19:50.276108+00:00","updated_at":"2026-07-05T11:19:50.276108+00:00"}