{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7VO2VR2TMH47JMXG2KHULANQGG","short_pith_number":"pith:7VO2VR2T","schema_version":"1.0","canonical_sha256":"fd5daac75361f9f4b2e6d28f4581b03194b4ac28d05070f4936c63d6598b7e7f","source":{"kind":"arxiv","id":"2605.17070","version":1},"attestation_state":"computed","paper":{"title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-05-16T16:38:51Z","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-"},"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":"2605.17070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T16:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"0d0376a60ebceccbe7b57bb496e1f19cd665d54b52b3ae8324f77bc7bff7f5e0","abstract_canon_sha256":"5b6c3e2263c6db5d29b5c96dcf5e203bfe9e285609a65c4495b9f0d7f15f37b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:39.130580Z","signature_b64":"/8nPpRcNYaA1/0Um3Zi041ILDH1Y3VIokovy2c3UD3sm4vx/cXLG3fehlITTp6ZHjc+wLt1BcPwqlbzQ0DmMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd5daac75361f9f4b2e6d28f4581b03194b4ac28d05070f4936c63d6598b7e7f","last_reissued_at":"2026-05-20T00:03:39.129936Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:39.129936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-05-16T16:38:51Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17070","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/2605.17070/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"dc276e7e09a0fda5bf8e7a66896bb6a1d22ea06e0057a416553e10955b34677d"},"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":"2605.17070","created_at":"2026-05-20T00:03:39.130072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17070v1","created_at":"2026-05-20T00:03:39.130072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17070","created_at":"2026-05-20T00:03:39.130072+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VO2VR2TMH47","created_at":"2026-05-20T00:03:39.130072+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VO2VR2TMH47JMXG","created_at":"2026-05-20T00:03:39.130072+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VO2VR2T","created_at":"2026-05-20T00:03:39.130072+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/7VO2VR2TMH47JMXG2KHULANQGG","json":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG.json","graph_json":"https://pith.science/api/pith-number/7VO2VR2TMH47JMXG2KHULANQGG/graph.json","events_json":"https://pith.science/api/pith-number/7VO2VR2TMH47JMXG2KHULANQGG/events.json","paper":"https://pith.science/paper/7VO2VR2T"},"agent_actions":{"view_html":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG","download_json":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG.json","view_paper":"https://pith.science/paper/7VO2VR2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17070&json=true","fetch_graph":"https://pith.science/api/pith-number/7VO2VR2TMH47JMXG2KHULANQGG/graph.json","fetch_events":"https://pith.science/api/pith-number/7VO2VR2TMH47JMXG2KHULANQGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG/action/storage_attestation","attest_author":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG/action/author_attestation","sign_citation":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG/action/citation_signature","submit_replication":"https://pith.science/pith/7VO2VR2TMH47JMXG2KHULANQGG/action/replication_record"}},"created_at":"2026-05-20T00:03:39.130072+00:00","updated_at":"2026-05-20T00:03:39.130072+00:00"}