{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HXWDAL3KD6FWKJ46AVZMQS2MHH","short_pith_number":"pith:HXWDAL3K","schema_version":"1.0","canonical_sha256":"3dec302f6a1f8b65279e0572c84b4c39c814885b05779a91ae17c2f0b64b99e1","source":{"kind":"arxiv","id":"2411.18711","version":4},"attestation_state":"computed","paper":{"title":"Evaluating Vision-Language Models as Evaluators in Path Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Erion Plaku, Mohamed Aghzal, Xiang Yue, Ziyu Yao","submitted_at":"2024-11-27T19:32:03Z","abstract_excerpt":"Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the planning framework as a helpful plan evaluator? In this work, we generalize this question to consider LLMs augmented with visual understanding, i.e., Vision-Language Models (VLMs). We introduce PathEval, a novel benchmark evaluating VLMs as plan evaluators in complex path-planning scenarios. Succeeding in the benchmark requires a VLM to b"},"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":"2411.18711","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T19:32:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4579d44efa409564060634b49f9a36389abf8c7ec4fecf6c215515d3c567cb8e","abstract_canon_sha256":"088e523f26aa5dc05347fb93e7b073e515e222d2450df95cc1c3f7d572ad2f5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:54.373555Z","signature_b64":"3jW4HET2mBMgZu52TG5K3WwO+oR7sXp/yJAc+v1OQDsxUAWy4qidGFYOTPt/Ju8nn05EQwFwW6V+EI/ZJ0/TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dec302f6a1f8b65279e0572c84b4c39c814885b05779a91ae17c2f0b64b99e1","last_reissued_at":"2026-07-05T11:03:54.373081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:54.373081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Vision-Language Models as Evaluators in Path Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Erion Plaku, Mohamed Aghzal, Xiang Yue, Ziyu Yao","submitted_at":"2024-11-27T19:32:03Z","abstract_excerpt":"Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the planning framework as a helpful plan evaluator? In this work, we generalize this question to consider LLMs augmented with visual understanding, i.e., Vision-Language Models (VLMs). We introduce PathEval, a novel benchmark evaluating VLMs as plan evaluators in complex path-planning scenarios. Succeeding in the benchmark requires a VLM to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18711","kind":"arxiv","version":4},"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/2411.18711/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":"2411.18711","created_at":"2026-07-05T11:03:54.373142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18711v4","created_at":"2026-07-05T11:03:54.373142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18711","created_at":"2026-07-05T11:03:54.373142+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXWDAL3KD6FW","created_at":"2026-07-05T11:03:54.373142+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXWDAL3KD6FWKJ46","created_at":"2026-07-05T11:03:54.373142+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXWDAL3K","created_at":"2026-07-05T11:03:54.373142+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/HXWDAL3KD6FWKJ46AVZMQS2MHH","json":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH.json","graph_json":"https://pith.science/api/pith-number/HXWDAL3KD6FWKJ46AVZMQS2MHH/graph.json","events_json":"https://pith.science/api/pith-number/HXWDAL3KD6FWKJ46AVZMQS2MHH/events.json","paper":"https://pith.science/paper/HXWDAL3K"},"agent_actions":{"view_html":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH","download_json":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH.json","view_paper":"https://pith.science/paper/HXWDAL3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18711&json=true","fetch_graph":"https://pith.science/api/pith-number/HXWDAL3KD6FWKJ46AVZMQS2MHH/graph.json","fetch_events":"https://pith.science/api/pith-number/HXWDAL3KD6FWKJ46AVZMQS2MHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH/action/storage_attestation","attest_author":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH/action/author_attestation","sign_citation":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH/action/citation_signature","submit_replication":"https://pith.science/pith/HXWDAL3KD6FWKJ46AVZMQS2MHH/action/replication_record"}},"created_at":"2026-07-05T11:03:54.373142+00:00","updated_at":"2026-07-05T11:03:54.373142+00:00"}