{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DHPJGU6SQVKBMDU6TD5JKZIT7O","short_pith_number":"pith:DHPJGU6S","schema_version":"1.0","canonical_sha256":"19de9353d28554160e9e98fa956513fb9a0f0f7c4181b3604b4fb9d1029449d5","source":{"kind":"arxiv","id":"2411.14484","version":1},"attestation_state":"computed","paper":{"title":"Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atharva Gundawar, Karthik Valmeekam, Mudit Verma, Subbarao Kambhampati","submitted_at":"2024-11-20T02:04:09Z","abstract_excerpt":"Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither robust nor predictable. This limitation can be addressed through compound LLM architectures where LLMs work in conjunction with other components to ensure reliability. In this paper, we present a technical evaluation of a compound LLM architecture--the LLM-Modulo framework. In this framework, an LLM is paired with a complete set of sound verifiers that valid"},"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":"2411.14484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T02:04:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5ce576325cc5ddd1ba6b22490970f4708c1eac62fcee14e54dc8f5d9a4bf1d9","abstract_canon_sha256":"9f0e295d9739c6036c93246495b937edc47b577cd6a95494b6452c02483c8e44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:51.922946Z","signature_b64":"BopL5ffGHytdCtYsHRETt4CJwjt7f4iVLn+FlN0Px9hdl9qkHVCs4ucRZxu8sFvvaEzT0zZK4ggjyBKlmohAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19de9353d28554160e9e98fa956513fb9a0f0f7c4181b3604b4fb9d1029449d5","last_reissued_at":"2026-07-05T09:38:51.922489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:51.922489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atharva Gundawar, Karthik Valmeekam, Mudit Verma, Subbarao Kambhampati","submitted_at":"2024-11-20T02:04:09Z","abstract_excerpt":"Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither robust nor predictable. This limitation can be addressed through compound LLM architectures where LLMs work in conjunction with other components to ensure reliability. In this paper, we present a technical evaluation of a compound LLM architecture--the LLM-Modulo framework. In this framework, an LLM is paired with a complete set of sound verifiers that valid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14484","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/2411.14484/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":"2411.14484","created_at":"2026-07-05T09:38:51.922538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14484v1","created_at":"2026-07-05T09:38:51.922538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14484","created_at":"2026-07-05T09:38:51.922538+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHPJGU6SQVKB","created_at":"2026-07-05T09:38:51.922538+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHPJGU6SQVKBMDU6","created_at":"2026-07-05T09:38:51.922538+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHPJGU6S","created_at":"2026-07-05T09:38:51.922538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.09629","citing_title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O","json":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O.json","graph_json":"https://pith.science/api/pith-number/DHPJGU6SQVKBMDU6TD5JKZIT7O/graph.json","events_json":"https://pith.science/api/pith-number/DHPJGU6SQVKBMDU6TD5JKZIT7O/events.json","paper":"https://pith.science/paper/DHPJGU6S"},"agent_actions":{"view_html":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O","download_json":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O.json","view_paper":"https://pith.science/paper/DHPJGU6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14484&json=true","fetch_graph":"https://pith.science/api/pith-number/DHPJGU6SQVKBMDU6TD5JKZIT7O/graph.json","fetch_events":"https://pith.science/api/pith-number/DHPJGU6SQVKBMDU6TD5JKZIT7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O/action/storage_attestation","attest_author":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O/action/author_attestation","sign_citation":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O/action/citation_signature","submit_replication":"https://pith.science/pith/DHPJGU6SQVKBMDU6TD5JKZIT7O/action/replication_record"}},"created_at":"2026-07-05T09:38:51.922538+00:00","updated_at":"2026-07-05T09:38:51.922538+00:00"}