{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HXWDAL3KD6FWKJ46AVZMQS2MHH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"088e523f26aa5dc05347fb93e7b073e515e222d2450df95cc1c3f7d572ad2f5d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T19:32:03Z","title_canon_sha256":"4579d44efa409564060634b49f9a36389abf8c7ec4fecf6c215515d3c567cb8e"},"schema_version":"1.0","source":{"id":"2411.18711","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18711","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18711v4","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18711","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"HXWDAL3KD6FW","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"HXWDAL3KD6FWKJ46","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"HXWDAL3K","created_at":"2026-07-05T11:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:d1000bcba24b201f9997c90e9902f30842e4e0cbb262c61db85c4d021d4af582","target":"graph","created_at":"2026-07-05T11:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.18711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Erion Plaku, Mohamed Aghzal, Xiang Yue, Ziyu Yao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T19:32:03Z","title":"Evaluating Vision-Language Models as Evaluators in Path Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18711","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a20a96752cafdb271dd0b3f9d34e97d0a4ebfaef1b0a533e6ca9791f3097dc4","target":"record","created_at":"2026-07-05T11:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"088e523f26aa5dc05347fb93e7b073e515e222d2450df95cc1c3f7d572ad2f5d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T19:32:03Z","title_canon_sha256":"4579d44efa409564060634b49f9a36389abf8c7ec4fecf6c215515d3c567cb8e"},"schema_version":"1.0","source":{"id":"2411.18711","kind":"arxiv","version":4}},"canonical_sha256":"3dec302f6a1f8b65279e0572c84b4c39c814885b05779a91ae17c2f0b64b99e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dec302f6a1f8b65279e0572c84b4c39c814885b05779a91ae17c2f0b64b99e1","first_computed_at":"2026-07-05T11:03:54.373081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:54.373081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3jW4HET2mBMgZu52TG5K3WwO+oR7sXp/yJAc+v1OQDsxUAWy4qidGFYOTPt/Ju8nn05EQwFwW6V+EI/ZJ0/TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:54.373555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18711","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a20a96752cafdb271dd0b3f9d34e97d0a4ebfaef1b0a533e6ca9791f3097dc4","sha256:d1000bcba24b201f9997c90e9902f30842e4e0cbb262c61db85c4d021d4af582"],"state_sha256":"7d1ca5ffb33354d50514ac27a86eed0183ae6301e2bb0c531c5c4ed642b72282"}