{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7VO2VR2TMH47JMXG2KHULANQGG","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":"5b6c3e2263c6db5d29b5c96dcf5e203bfe9e285609a65c4495b9f0d7f15f37b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T16:38:51Z","title_canon_sha256":"0d0376a60ebceccbe7b57bb496e1f19cd665d54b52b3ae8324f77bc7bff7f5e0"},"schema_version":"1.0","source":{"id":"2605.17070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17070","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17070v1","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17070","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"7VO2VR2TMH47","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"7VO2VR2TMH47JMXG","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"7VO2VR2T","created_at":"2026-05-20T00:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:a55a3d16f804c91dc47fdcbf4b0b90f6b103fd08dc7e9c2864b5db195701555b","target":"graph","created_at":"2026-05-20T00:03:39Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.814637Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.753043Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17070/integrity.json","findings":[],"snapshot_sha256":"dc276e7e09a0fda5bf8e7a66896bb6a1d22ea06e0057a416553e10955b34677d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, existing benchmarks often rely on question-answering or multiple-choice formats. These protocols allow models to exploit linguistic priors rather than demonstrating genuine visual grounding. To address this, we present EPIC-Bench, Embodied PerceptIon BenChmark, a fine-grained grounding benchmark designed to systematically evaluate the visual perceptual capabilities of VLMs in real-world embodied environments. Comprising 6.6k meticulously annotated tuples (Image, Text, Mask), EPIC-","authors_text":"Bin Shen, Han Dong, Haoyuan Shi, Haozhe Shan, Jiayu Hu, Lizhen Qu, Xiancong Ren, Xiaozhu Ju, Yingji Zhang, Yi Zhang, Yong Dai, Zenglin Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T16:38:51Z","title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17070","kind":"arxiv","version":1},"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":"sha256:908a1e26246e9a57c4ca4fb3404734af304d62464881013255fffcf7ecdf3e43","target":"record","created_at":"2026-05-20T00:03:39Z","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":"5b6c3e2263c6db5d29b5c96dcf5e203bfe9e285609a65c4495b9f0d7f15f37b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T16:38:51Z","title_canon_sha256":"0d0376a60ebceccbe7b57bb496e1f19cd665d54b52b3ae8324f77bc7bff7f5e0"},"schema_version":"1.0","source":{"id":"2605.17070","kind":"arxiv","version":1}},"canonical_sha256":"fd5daac75361f9f4b2e6d28f4581b03194b4ac28d05070f4936c63d6598b7e7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd5daac75361f9f4b2e6d28f4581b03194b4ac28d05070f4936c63d6598b7e7f","first_computed_at":"2026-05-20T00:03:39.129936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:39.129936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/8nPpRcNYaA1/0Um3Zi041ILDH1Y3VIokovy2c3UD3sm4vx/cXLG3fehlITTp6ZHjc+wLt1BcPwqlbzQ0DmMAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:39.130580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:908a1e26246e9a57c4ca4fb3404734af304d62464881013255fffcf7ecdf3e43","sha256:a55a3d16f804c91dc47fdcbf4b0b90f6b103fd08dc7e9c2864b5db195701555b"],"state_sha256":"f97ee040a855c6f07b722a34de84d38e336586cf94982d86a213e3146cb81c6d"}