{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKLD5AXNYN5FOX36J4UOAKOO63","short_pith_number":"pith:UKLD5AXN","schema_version":"1.0","canonical_sha256":"a2963e82edc37a575f7e4f28e029cef6db96ed4440c1bbf8adbb6e5e3ad3a256","source":{"kind":"arxiv","id":"2404.15676","version":3},"attestation_state":"computed","paper":{"title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julian McAuley, Mingyan Li, Rui Wang, Shuai Li, Tong Yu, Xiang Chen, Xu Liu, Yu Xia","submitted_at":"2024-04-24T06:12:00Z","abstract_excerpt":"Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address various challenges across diverse domains and tasks involving LLMs. In this paper, we provide a comprehensive survey of Chain-of-X methods for LLMs in different contexts. Specifically, we categorize them by taxonomies of nodes, i.e., the X in CoX, and application tasks. We also discuss the findings and implications of existing CoX metho"},"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":"2404.15676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T06:12:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"805fe599c24bf1bbb35f48525ecf7694b8626835457c33caa5cd2ef04c279018","abstract_canon_sha256":"469d996e3c30b578f1bd50b99834d00893e20c03fcd0bcaf1b32660e90bf09f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:07.406746Z","signature_b64":"Cf7SsZRHNgNb3NbH1Co7MuIvrRiK62ZSXn7cd7x5YtCGvjW+P6T9/9pJcGNS5yTbWTEE6+cOvcMhmq8BVOupBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2963e82edc37a575f7e4f28e029cef6db96ed4440c1bbf8adbb6e5e3ad3a256","last_reissued_at":"2026-07-05T10:10:07.406249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:07.406249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julian McAuley, Mingyan Li, Rui Wang, Shuai Li, Tong Yu, Xiang Chen, Xu Liu, Yu Xia","submitted_at":"2024-04-24T06:12:00Z","abstract_excerpt":"Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address various challenges across diverse domains and tasks involving LLMs. In this paper, we provide a comprehensive survey of Chain-of-X methods for LLMs in different contexts. Specifically, we categorize them by taxonomies of nodes, i.e., the X in CoX, and application tasks. We also discuss the findings and implications of existing CoX metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15676","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/2404.15676/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":"2404.15676","created_at":"2026-07-05T10:10:07.406306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15676v3","created_at":"2026-07-05T10:10:07.406306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15676","created_at":"2026-07-05T10:10:07.406306+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKLD5AXNYN5F","created_at":"2026-07-05T10:10:07.406306+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKLD5AXNYN5FOX36","created_at":"2026-07-05T10:10:07.406306+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKLD5AXN","created_at":"2026-07-05T10:10:07.406306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.27578","citing_title":"What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63","json":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63.json","graph_json":"https://pith.science/api/pith-number/UKLD5AXNYN5FOX36J4UOAKOO63/graph.json","events_json":"https://pith.science/api/pith-number/UKLD5AXNYN5FOX36J4UOAKOO63/events.json","paper":"https://pith.science/paper/UKLD5AXN"},"agent_actions":{"view_html":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63","download_json":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63.json","view_paper":"https://pith.science/paper/UKLD5AXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15676&json=true","fetch_graph":"https://pith.science/api/pith-number/UKLD5AXNYN5FOX36J4UOAKOO63/graph.json","fetch_events":"https://pith.science/api/pith-number/UKLD5AXNYN5FOX36J4UOAKOO63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63/action/storage_attestation","attest_author":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63/action/author_attestation","sign_citation":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63/action/citation_signature","submit_replication":"https://pith.science/pith/UKLD5AXNYN5FOX36J4UOAKOO63/action/replication_record"}},"created_at":"2026-07-05T10:10:07.406306+00:00","updated_at":"2026-07-05T10:10:07.406306+00:00"}