{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSIMGL6NV4AOUPN553FMZPXTAN","short_pith_number":"pith:SSIMGL6N","schema_version":"1.0","canonical_sha256":"9490c32fcdaf00ea3dbdeecaccbef3035f46db8a39756ed7b653da39b5e82128","source":{"kind":"arxiv","id":"2412.08281","version":1},"attestation_state":"computed","paper":{"title":"Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Gabin An, Naryeong Kim, Shin Yoo, Sungmin Kang","submitted_at":"2024-12-11T10:56:47Z","abstract_excerpt":"Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, "},"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":"2412.08281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-11T10:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"2c69028932a6cd7c2f20b0ace3b35373b49c84c00f46689965ba1b43f9caea23","abstract_canon_sha256":"b3bd7d35fd43019cbc19845d46e5066aac7aada614a1c1f5309d898111334a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:47.638205Z","signature_b64":"IKbaJOnJjbiO/b4VZ59HDwhW1Aq7DIkA0t8GqT8S16s5IYD53JQxK6PPmQEC54uU+VhCA0aEGsXTfvEJGWyEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9490c32fcdaf00ea3dbdeecaccbef3035f46db8a39756ed7b653da39b5e82128","last_reissued_at":"2026-07-05T09:47:47.637744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:47.637744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Gabin An, Naryeong Kim, Shin Yoo, Sungmin Kang","submitted_at":"2024-12-11T10:56:47Z","abstract_excerpt":"Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08281","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/2412.08281/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":"2412.08281","created_at":"2026-07-05T09:47:47.637794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08281v1","created_at":"2026-07-05T09:47:47.637794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08281","created_at":"2026-07-05T09:47:47.637794+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSIMGL6NV4AO","created_at":"2026-07-05T09:47:47.637794+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSIMGL6NV4AOUPN5","created_at":"2026-07-05T09:47:47.637794+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSIMGL6N","created_at":"2026-07-05T09:47:47.637794+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/SSIMGL6NV4AOUPN553FMZPXTAN","json":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN.json","graph_json":"https://pith.science/api/pith-number/SSIMGL6NV4AOUPN553FMZPXTAN/graph.json","events_json":"https://pith.science/api/pith-number/SSIMGL6NV4AOUPN553FMZPXTAN/events.json","paper":"https://pith.science/paper/SSIMGL6N"},"agent_actions":{"view_html":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN","download_json":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN.json","view_paper":"https://pith.science/paper/SSIMGL6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08281&json=true","fetch_graph":"https://pith.science/api/pith-number/SSIMGL6NV4AOUPN553FMZPXTAN/graph.json","fetch_events":"https://pith.science/api/pith-number/SSIMGL6NV4AOUPN553FMZPXTAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN/action/storage_attestation","attest_author":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN/action/author_attestation","sign_citation":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN/action/citation_signature","submit_replication":"https://pith.science/pith/SSIMGL6NV4AOUPN553FMZPXTAN/action/replication_record"}},"created_at":"2026-07-05T09:47:47.637794+00:00","updated_at":"2026-07-05T09:47:47.637794+00:00"}