{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PDBKIAAY6XFPIRED34NXBE6X3N","short_pith_number":"pith:PDBKIAAY","schema_version":"1.0","canonical_sha256":"78c2a40018f5caf44483df1b7093d7db69ed37b7e0467b351fd5262dede26452","source":{"kind":"arxiv","id":"2601.18723","version":2},"attestation_state":"computed","paper":{"title":"Eval-Actions: Fine-Grained Execution Quality Evaluation for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hong Liu, Juyi Sheng, Mengyuan Liu, Peiming Li, Tianming Xu, Tiantian Xu, Ziyi Wang","submitted_at":"2026-01-26T17:47:42Z","abstract_excerpt":"Although Vision--Action (VA) and Vision--Language--Action (VLA) policies have advanced robotic manipulation, their evaluation remains dominated by binary success rates, which obscure process-level differences among executions that complete the same task. We introduce Eval-Actions, a diagnostic evaluation methodology and real-robot benchmark for fine-grained execution-quality assessment of learned manipulation policies. Eval-Actions combines criteria-based Expert Grading (EG), Rank-Guided (RG) labels that align measurable motion indicators with expert rankings, and Chain-of-Thought-style (CoT) "},"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":"2601.18723","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-26T17:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"62649f5b99fe1b04af9d4aa39675f43b55667adce27867b3fb5c2002e0543d2e","abstract_canon_sha256":"e24db896dec235d606f4c3f2cece1d632611bf25b1b0e411c24bf386c2382f09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:33.026869Z","signature_b64":"biidOT2/aBc+pZPel8AbMm2Fhk+S0QBe3bkFFdem6j4QkBIvEJzndcMVx2g1BSdyRp6IpK0qO15uerQ4LLmsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c2a40018f5caf44483df1b7093d7db69ed37b7e0467b351fd5262dede26452","last_reissued_at":"2026-06-30T01:17:33.026233Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:33.026233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eval-Actions: Fine-Grained Execution Quality Evaluation for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hong Liu, Juyi Sheng, Mengyuan Liu, Peiming Li, Tianming Xu, Tiantian Xu, Ziyi Wang","submitted_at":"2026-01-26T17:47:42Z","abstract_excerpt":"Although Vision--Action (VA) and Vision--Language--Action (VLA) policies have advanced robotic manipulation, their evaluation remains dominated by binary success rates, which obscure process-level differences among executions that complete the same task. We introduce Eval-Actions, a diagnostic evaluation methodology and real-robot benchmark for fine-grained execution-quality assessment of learned manipulation policies. Eval-Actions combines criteria-based Expert Grading (EG), Rank-Guided (RG) labels that align measurable motion indicators with expert rankings, and Chain-of-Thought-style (CoT) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18723","kind":"arxiv","version":2},"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/2601.18723/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":"2601.18723","created_at":"2026-06-30T01:17:33.026302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18723v2","created_at":"2026-06-30T01:17:33.026302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18723","created_at":"2026-06-30T01:17:33.026302+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDBKIAAY6XFP","created_at":"2026-06-30T01:17:33.026302+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDBKIAAY6XFPIRED","created_at":"2026-06-30T01:17:33.026302+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDBKIAAY","created_at":"2026-06-30T01:17:33.026302+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/PDBKIAAY6XFPIRED34NXBE6X3N","json":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N.json","graph_json":"https://pith.science/api/pith-number/PDBKIAAY6XFPIRED34NXBE6X3N/graph.json","events_json":"https://pith.science/api/pith-number/PDBKIAAY6XFPIRED34NXBE6X3N/events.json","paper":"https://pith.science/paper/PDBKIAAY"},"agent_actions":{"view_html":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N","download_json":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N.json","view_paper":"https://pith.science/paper/PDBKIAAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18723&json=true","fetch_graph":"https://pith.science/api/pith-number/PDBKIAAY6XFPIRED34NXBE6X3N/graph.json","fetch_events":"https://pith.science/api/pith-number/PDBKIAAY6XFPIRED34NXBE6X3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N/action/storage_attestation","attest_author":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N/action/author_attestation","sign_citation":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N/action/citation_signature","submit_replication":"https://pith.science/pith/PDBKIAAY6XFPIRED34NXBE6X3N/action/replication_record"}},"created_at":"2026-06-30T01:17:33.026302+00:00","updated_at":"2026-06-30T01:17:33.026302+00:00"}