{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZFQSFAL67D22RFFXJIU2HBOMZ","short_pith_number":"pith:LZFQSFAL","schema_version":"1.0","canonical_sha256":"5e4b09140bf7c7ad44a5ba514d1c2e6674c9835ef2c5ebd75a516235468843ee","source":{"kind":"arxiv","id":"2305.14750","version":1},"attestation_state":"computed","paper":{"title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hari Sundaram, Jie Huang, Kevin Chen-Chuan Chang, Nishant Balepur, Samraj Moorjani","submitted_at":"2023-05-24T05:53:11Z","abstract_excerpt":"When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question. While existing self-evaluation techniques aim to detect if such answers are correct, these techniques are unable to determine which criteria of the question are satisfied by the generated answers. To address this issue, we propose answer-based claim decomposition (ABCD), a prompting strategy that decomposes questions into a series of true/false claims that can be used to verify which criteria of the input question an answer satisfies. Using the decomposed ABCD cl"},"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":"2305.14750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T05:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"3324f5a640c4f3f84f37cca5717f3d4b732e9c6eb4c33aa6a1f881ec0da87237","abstract_canon_sha256":"68eaf702877026156b7384ed3b6155602105fcdede5e238066cc31afcf0384c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:27.551391Z","signature_b64":"ikpq36UJbmHI+gtjFRk55dPlEe0zJzaS78VGHuKc9+/pWxmKw8Df2ZG3IQvBDkZ6uxx4RJPNOCpfbWcD6AQgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4b09140bf7c7ad44a5ba514d1c2e6674c9835ef2c5ebd75a516235468843ee","last_reissued_at":"2026-07-05T06:13:27.550966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:27.550966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hari Sundaram, Jie Huang, Kevin Chen-Chuan Chang, Nishant Balepur, Samraj Moorjani","submitted_at":"2023-05-24T05:53:11Z","abstract_excerpt":"When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question. While existing self-evaluation techniques aim to detect if such answers are correct, these techniques are unable to determine which criteria of the question are satisfied by the generated answers. To address this issue, we propose answer-based claim decomposition (ABCD), a prompting strategy that decomposes questions into a series of true/false claims that can be used to verify which criteria of the input question an answer satisfies. Using the decomposed ABCD cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14750","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/2305.14750/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":"2305.14750","created_at":"2026-07-05T06:13:27.551023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14750v1","created_at":"2026-07-05T06:13:27.551023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14750","created_at":"2026-07-05T06:13:27.551023+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZFQSFAL67D2","created_at":"2026-07-05T06:13:27.551023+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZFQSFAL67D22RFF","created_at":"2026-07-05T06:13:27.551023+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZFQSFAL","created_at":"2026-07-05T06:13:27.551023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04480","citing_title":"TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ","json":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ.json","graph_json":"https://pith.science/api/pith-number/LZFQSFAL67D22RFFXJIU2HBOMZ/graph.json","events_json":"https://pith.science/api/pith-number/LZFQSFAL67D22RFFXJIU2HBOMZ/events.json","paper":"https://pith.science/paper/LZFQSFAL"},"agent_actions":{"view_html":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ","download_json":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ.json","view_paper":"https://pith.science/paper/LZFQSFAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14750&json=true","fetch_graph":"https://pith.science/api/pith-number/LZFQSFAL67D22RFFXJIU2HBOMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZFQSFAL67D22RFFXJIU2HBOMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ/action/storage_attestation","attest_author":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ/action/author_attestation","sign_citation":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ/action/citation_signature","submit_replication":"https://pith.science/pith/LZFQSFAL67D22RFFXJIU2HBOMZ/action/replication_record"}},"created_at":"2026-07-05T06:13:27.551023+00:00","updated_at":"2026-07-05T06:13:27.551023+00:00"}