{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FMCY7FHYVQAQABZHCLSULCLNNS","short_pith_number":"pith:FMCY7FHY","schema_version":"1.0","canonical_sha256":"2b058f94f8ac0100072712e545896d6c9c4fc9e6e30f538eac405e037ebdec00","source":{"kind":"arxiv","id":"2502.01828","version":3},"attestation_state":"computed","paper":{"title":"From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Bajcsy, Gokul Swamy, Ran Tian, Yilin Wu","submitted_at":"2025-02-03T21:11:02Z","abstract_excerpt":"While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deployment-time. Policy steering offers an elegant solution to reducing the chance of failure by using an external verifier to select from low-level actions proposed by an imperfect generative policy. Here, one might hope to use a Vision Language Model (VLM) as a verifier, leveraging its open-world reasoning capabilities. However, off-the-shelf VLMs struggle to understand the consequences of low-level robot actions as they"},"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":"2502.01828","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T21:11:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff375ba982a89d3af1b0c67098249357432f095338affa86bf4c486e286d3ae1","abstract_canon_sha256":"0fbc5005a93009051f6d4caab2ee691bf5494f0b7f5f5a7de550de63a7d38afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:33.400501Z","signature_b64":"Cagp1v/UKwKnB/s572ihUfZH6WCj9zi4p330kfR4Di6fUKFvlyKXyPoUST2OjgjTEiMw1akwh6Hcr3BHt7+yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b058f94f8ac0100072712e545896d6c9c4fc9e6e30f538eac405e037ebdec00","last_reissued_at":"2026-07-05T10:57:33.400003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:33.400003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Bajcsy, Gokul Swamy, Ran Tian, Yilin Wu","submitted_at":"2025-02-03T21:11:02Z","abstract_excerpt":"While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deployment-time. Policy steering offers an elegant solution to reducing the chance of failure by using an external verifier to select from low-level actions proposed by an imperfect generative policy. Here, one might hope to use a Vision Language Model (VLM) as a verifier, leveraging its open-world reasoning capabilities. However, off-the-shelf VLMs struggle to understand the consequences of low-level robot actions as they"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01828","kind":"arxiv","version":3},"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/2502.01828/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":"2502.01828","created_at":"2026-07-05T10:57:33.400058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01828v3","created_at":"2026-07-05T10:57:33.400058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01828","created_at":"2026-07-05T10:57:33.400058+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMCY7FHYVQAQ","created_at":"2026-07-05T10:57:33.400058+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMCY7FHYVQAQABZH","created_at":"2026-07-05T10:57:33.400058+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMCY7FHY","created_at":"2026-07-05T10:57:33.400058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26588","citing_title":"Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22998","citing_title":"TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21572","citing_title":"Robot Critics that Sweat the Small Stuff","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18589","citing_title":"DREAM-Chunk: Reactive Action Chunking with Latent World Model","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12366","citing_title":"APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03954","citing_title":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01036","citing_title":"Position: Good Embodied Reward Models Need Bad Behavior Data","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS","json":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS.json","graph_json":"https://pith.science/api/pith-number/FMCY7FHYVQAQABZHCLSULCLNNS/graph.json","events_json":"https://pith.science/api/pith-number/FMCY7FHYVQAQABZHCLSULCLNNS/events.json","paper":"https://pith.science/paper/FMCY7FHY"},"agent_actions":{"view_html":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS","download_json":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS.json","view_paper":"https://pith.science/paper/FMCY7FHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01828&json=true","fetch_graph":"https://pith.science/api/pith-number/FMCY7FHYVQAQABZHCLSULCLNNS/graph.json","fetch_events":"https://pith.science/api/pith-number/FMCY7FHYVQAQABZHCLSULCLNNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS/action/storage_attestation","attest_author":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS/action/author_attestation","sign_citation":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS/action/citation_signature","submit_replication":"https://pith.science/pith/FMCY7FHYVQAQABZHCLSULCLNNS/action/replication_record"}},"created_at":"2026-07-05T10:57:33.400058+00:00","updated_at":"2026-07-05T10:57:33.400058+00:00"}