{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BEHDYHJVXL4MUQXD4GL24V2B3Y","short_pith_number":"pith:BEHDYHJV","schema_version":"1.0","canonical_sha256":"090e3c1d35baf8ca42e3e197ae5741de1e4e943baa63a2c2f5116935a2781d80","source":{"kind":"arxiv","id":"2410.00371","version":1},"attestation_state":"computed","paper":{"title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Dieter Fox, Jiafei Duan, Nishanth Kumar, Ranjay Krishna, Shulin Tian, Wentao Yuan, Wilbert Pumacay, Yijie Guo, Yi Ru Wang","submitted_at":"2024-10-01T03:47:00Z","abstract_excerpt":"Robotic manipulation in open-world settings requires not only task execution but also the ability to detect and learn from failures. While recent advances in vision-language models (VLMs) and large language models (LLMs) have improved robots' spatial reasoning and problem-solving abilities, they still struggle with failure recognition, limiting their real-world applicability. We introduce AHA, an open-source VLM designed to detect and reason about failures in robotic manipulation using natural language. By framing failure detection as a free-form reasoning task, AHA identifies failures and pro"},"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":"2410.00371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T03:47:00Z","cross_cats_sorted":[],"title_canon_sha256":"2b506cc8502b8cf6e2a761f93c0cec3df28044d8f075abaee55856507ffe4a50","abstract_canon_sha256":"561b714e25a28c918a5356a0db401478fb5c3c3c9a6ab8b51b0bed2dd1bb20a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:03.996157Z","signature_b64":"1Y4vz8O1FoFoIHDu+bl38YR/jF4/+w9Dxgeb/u2DME1AkjETAhGddV3nt8Nc6lYDVIu3lpUo5+fey40nKtm7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"090e3c1d35baf8ca42e3e197ae5741de1e4e943baa63a2c2f5116935a2781d80","last_reissued_at":"2026-07-05T09:14:03.995721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:03.995721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Dieter Fox, Jiafei Duan, Nishanth Kumar, Ranjay Krishna, Shulin Tian, Wentao Yuan, Wilbert Pumacay, Yijie Guo, Yi Ru Wang","submitted_at":"2024-10-01T03:47:00Z","abstract_excerpt":"Robotic manipulation in open-world settings requires not only task execution but also the ability to detect and learn from failures. While recent advances in vision-language models (VLMs) and large language models (LLMs) have improved robots' spatial reasoning and problem-solving abilities, they still struggle with failure recognition, limiting their real-world applicability. We introduce AHA, an open-source VLM designed to detect and reason about failures in robotic manipulation using natural language. By framing failure detection as a free-form reasoning task, AHA identifies failures and pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00371","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/2410.00371/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":"2410.00371","created_at":"2026-07-05T09:14:03.995770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00371v1","created_at":"2026-07-05T09:14:03.995770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00371","created_at":"2026-07-05T09:14:03.995770+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEHDYHJVXL4M","created_at":"2026-07-05T09:14:03.995770+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEHDYHJVXL4MUQXD","created_at":"2026-07-05T09:14:03.995770+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEHDYHJV","created_at":"2026-07-05T09:14:03.995770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23085","citing_title":"Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21572","citing_title":"Robot Critics that Sweat the Small Stuff","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19598","citing_title":"Fail-RAG : A Retrieval Augmented Generation Informed Framework for Robot Failure Identification","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18328","citing_title":"Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08542","citing_title":"When Video Misreads: Closed-Loop Distillation of Reading Heuristics for Exploratory Manipulation Trace QA","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08508","citing_title":"ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01088","citing_title":"ROSA: A Robotics Foundation Model Serving System for Robot Factories","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03385","citing_title":"Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29605","citing_title":"VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02818","citing_title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16056","citing_title":"Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16815","citing_title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21723","citing_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19268","citing_title":"Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22519","citing_title":"Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08434","citing_title":"Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11750","citing_title":"DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11951","citing_title":"From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08434","citing_title":"Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19839","citing_title":"Environmental Understanding Vision-Language Model for Embodied Agent","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07395","citing_title":"A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y","json":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y.json","graph_json":"https://pith.science/api/pith-number/BEHDYHJVXL4MUQXD4GL24V2B3Y/graph.json","events_json":"https://pith.science/api/pith-number/BEHDYHJVXL4MUQXD4GL24V2B3Y/events.json","paper":"https://pith.science/paper/BEHDYHJV"},"agent_actions":{"view_html":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y","download_json":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y.json","view_paper":"https://pith.science/paper/BEHDYHJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00371&json=true","fetch_graph":"https://pith.science/api/pith-number/BEHDYHJVXL4MUQXD4GL24V2B3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/BEHDYHJVXL4MUQXD4GL24V2B3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y/action/storage_attestation","attest_author":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y/action/author_attestation","sign_citation":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y/action/citation_signature","submit_replication":"https://pith.science/pith/BEHDYHJVXL4MUQXD4GL24V2B3Y/action/replication_record"}},"created_at":"2026-07-05T09:14:03.995770+00:00","updated_at":"2026-07-05T09:14:03.995770+00:00"}