{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EBTOWITLG5YZJGJDPNIO6FSB52","short_pith_number":"pith:EBTOWITL","schema_version":"1.0","canonical_sha256":"2066eb226b37719499237b50ef1641eea9a104363d73ac37f9906369e1ec39e9","source":{"kind":"arxiv","id":"2507.08224","version":2},"attestation_state":"computed","paper":{"title":"Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Chan Young Park, Dipika Khullar, Jillian Fisher, Marius Memmel, Seoho Yun, Yejin Choi","submitted_at":"2025-07-11T00:17:08Z","abstract_excerpt":"Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward more perceptually grounded plans, but current methods either rely on expensive, large-scale models or are constrained to narrow simulation settings. We introduce SelfReVision, a lightweight and scalable self-improvement framework for vision-language procedural planning. SelfReVision enables small VLMs to iteratively critique, revise, and verify their own plans"},"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":"2507.08224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-11T00:17:08Z","cross_cats_sorted":[],"title_canon_sha256":"f19e136b35d0eae5c5519449899a0543707da8c41531f32719da5726d5eec656","abstract_canon_sha256":"fa1c3f0bb5baf6b5a774e4b7ede02af5fc6d8ed6bdb873da854e563969d316ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:56.522828Z","signature_b64":"bEdgKDI9DmY5iN6YUvQDgIR2kd3EBC40/04JSS5OsW40Zi7SrvLq78rLvXDzBpgMKMdX/ARnsWl4tThEuNlmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2066eb226b37719499237b50ef1641eea9a104363d73ac37f9906369e1ec39e9","last_reissued_at":"2026-07-05T11:39:56.522328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:56.522328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Chan Young Park, Dipika Khullar, Jillian Fisher, Marius Memmel, Seoho Yun, Yejin Choi","submitted_at":"2025-07-11T00:17:08Z","abstract_excerpt":"Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward more perceptually grounded plans, but current methods either rely on expensive, large-scale models or are constrained to narrow simulation settings. We introduce SelfReVision, a lightweight and scalable self-improvement framework for vision-language procedural planning. SelfReVision enables small VLMs to iteratively critique, revise, and verify their own plans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08224","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/2507.08224/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":"2507.08224","created_at":"2026-07-05T11:39:56.522392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08224v2","created_at":"2026-07-05T11:39:56.522392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08224","created_at":"2026-07-05T11:39:56.522392+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBTOWITLG5YZ","created_at":"2026-07-05T11:39:56.522392+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBTOWITLG5YZJGJD","created_at":"2026-07-05T11:39:56.522392+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBTOWITL","created_at":"2026-07-05T11:39:56.522392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13775","citing_title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52","json":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52.json","graph_json":"https://pith.science/api/pith-number/EBTOWITLG5YZJGJDPNIO6FSB52/graph.json","events_json":"https://pith.science/api/pith-number/EBTOWITLG5YZJGJDPNIO6FSB52/events.json","paper":"https://pith.science/paper/EBTOWITL"},"agent_actions":{"view_html":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52","download_json":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52.json","view_paper":"https://pith.science/paper/EBTOWITL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08224&json=true","fetch_graph":"https://pith.science/api/pith-number/EBTOWITLG5YZJGJDPNIO6FSB52/graph.json","fetch_events":"https://pith.science/api/pith-number/EBTOWITLG5YZJGJDPNIO6FSB52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52/action/storage_attestation","attest_author":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52/action/author_attestation","sign_citation":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52/action/citation_signature","submit_replication":"https://pith.science/pith/EBTOWITLG5YZJGJDPNIO6FSB52/action/replication_record"}},"created_at":"2026-07-05T11:39:56.522392+00:00","updated_at":"2026-07-05T11:39:56.522392+00:00"}