{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5PDEUTS7MD7NP5227GA6EUERC","short_pith_number":"pith:O5PDEUTS","schema_version":"1.0","canonical_sha256":"775e325272fb07f6bfbad7cc0f128488a296c8839fc960e7225d2fa59d746922","source":{"kind":"arxiv","id":"2511.18685","version":4},"attestation_state":"computed","paper":{"title":"Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Baigui Sun, Chao Xu, Dayong Liu, Jiankang Deng, Juncheng Wang, Suyu Zhang, Weihong Chen, Yang Liu","submitted_at":"2025-11-24T02:02:29Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 question-answer pairs spanning three evaluation paradigms targeting f"},"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":"2511.18685","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T02:02:29Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d07d080704ecad7bace1fed51738d56df85f2109a77f848a9cf529bc701abae2","abstract_canon_sha256":"45069f76a0d18eb28e9e04ca2fd9e534302d5fabdaa42280650d86eae1b85b73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:21:43.027718Z","signature_b64":"DM80w2b7PvVtb6jKXO7MVwSQHUet+QGpdz/pvrqW7xFsGb2BCT56xq6sAgBalvZ2gmC4d3FAPPg9SjsDmTxIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"775e325272fb07f6bfbad7cc0f128488a296c8839fc960e7225d2fa59d746922","last_reissued_at":"2026-07-16T01:21:43.026724Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:21:43.026724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Baigui Sun, Chao Xu, Dayong Liu, Jiankang Deng, Juncheng Wang, Suyu Zhang, Weihong Chen, Yang Liu","submitted_at":"2025-11-24T02:02:29Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 question-answer pairs spanning three evaluation paradigms targeting f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18685","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/2511.18685/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":"2511.18685","created_at":"2026-07-16T01:21:43.027170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18685v4","created_at":"2026-07-16T01:21:43.027170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18685","created_at":"2026-07-16T01:21:43.027170+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5PDEUTS7MD7","created_at":"2026-07-16T01:21:43.027170+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5PDEUTS7MD7NP52","created_at":"2026-07-16T01:21:43.027170+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5PDEUTS","created_at":"2026-07-16T01:21:43.027170+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/O5PDEUTS7MD7NP5227GA6EUERC","json":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC.json","graph_json":"https://pith.science/api/pith-number/O5PDEUTS7MD7NP5227GA6EUERC/graph.json","events_json":"https://pith.science/api/pith-number/O5PDEUTS7MD7NP5227GA6EUERC/events.json","paper":"https://pith.science/paper/O5PDEUTS"},"agent_actions":{"view_html":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC","download_json":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC.json","view_paper":"https://pith.science/paper/O5PDEUTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18685&json=true","fetch_graph":"https://pith.science/api/pith-number/O5PDEUTS7MD7NP5227GA6EUERC/graph.json","fetch_events":"https://pith.science/api/pith-number/O5PDEUTS7MD7NP5227GA6EUERC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC/action/storage_attestation","attest_author":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC/action/author_attestation","sign_citation":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC/action/citation_signature","submit_replication":"https://pith.science/pith/O5PDEUTS7MD7NP5227GA6EUERC/action/replication_record"}},"created_at":"2026-07-16T01:21:43.027170+00:00","updated_at":"2026-07-16T01:21:43.027170+00:00"}