{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JOJPMRNFBHEA4ICWRHHISTMBST","short_pith_number":"pith:JOJPMRNF","schema_version":"1.0","canonical_sha256":"4b92f645a509c80e205689ce894d8194f9cc977f0dc7fe4848f2495f37f5f55a","source":{"kind":"arxiv","id":"2502.17894","version":2},"attestation_state":"computed","paper":{"title":"FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dongbin Zhao, Haoran Li, He Wang, Jilong Wang, Weiheng Liu, Wenbo Cui, Xuesong Shi, Yuxuan Kuang, Yuxuan Wan, Zhizheng Zhang","submitted_at":"2025-02-25T06:32:42Z","abstract_excerpt":"Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, making safe action generation particularly difficult. Under such partial observability, effective policies must not only generalize across diverse objects and layouts but also reason about occlusion to avoid collisions. However, collecting large-scale real-world data for this task remains prohibitively expensive, leaving this problem largely unsolved. In this paper, we introduce FetchBot, a sim-to-real framework for this "},"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":"2502.17894","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-25T06:32:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"65faf54b1fbd027128dfc0d29b5dc96f38819c237b3d5c2fda8a438c40b1fee2","abstract_canon_sha256":"f430dfc6f61deaf6f1e0d441e26f0a5206e85655af1b56dc34d830c327c242a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:25.317098Z","signature_b64":"0OqlDDLZdcQ0NgW6i7b6cEB1ZeHJrky1PedbZvJaSTczoN+o1/x9zc6ztlsLdPr8Mvml2jf6IPytDQObzBaCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b92f645a509c80e205689ce894d8194f9cc977f0dc7fe4848f2495f37f5f55a","last_reissued_at":"2026-07-05T11:58:25.316592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:25.316592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dongbin Zhao, Haoran Li, He Wang, Jilong Wang, Weiheng Liu, Wenbo Cui, Xuesong Shi, Yuxuan Kuang, Yuxuan Wan, Zhizheng Zhang","submitted_at":"2025-02-25T06:32:42Z","abstract_excerpt":"Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, making safe action generation particularly difficult. Under such partial observability, effective policies must not only generalize across diverse objects and layouts but also reason about occlusion to avoid collisions. However, collecting large-scale real-world data for this task remains prohibitively expensive, leaving this problem largely unsolved. In this paper, we introduce FetchBot, a sim-to-real framework for this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17894","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/2502.17894/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":"2502.17894","created_at":"2026-07-05T11:58:25.316664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17894v2","created_at":"2026-07-05T11:58:25.316664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17894","created_at":"2026-07-05T11:58:25.316664+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOJPMRNFBHEA","created_at":"2026-07-05T11:58:25.316664+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOJPMRNFBHEA4ICW","created_at":"2026-07-05T11:58:25.316664+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOJPMRNF","created_at":"2026-07-05T11:58:25.316664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19297","citing_title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST","json":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST.json","graph_json":"https://pith.science/api/pith-number/JOJPMRNFBHEA4ICWRHHISTMBST/graph.json","events_json":"https://pith.science/api/pith-number/JOJPMRNFBHEA4ICWRHHISTMBST/events.json","paper":"https://pith.science/paper/JOJPMRNF"},"agent_actions":{"view_html":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST","download_json":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST.json","view_paper":"https://pith.science/paper/JOJPMRNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17894&json=true","fetch_graph":"https://pith.science/api/pith-number/JOJPMRNFBHEA4ICWRHHISTMBST/graph.json","fetch_events":"https://pith.science/api/pith-number/JOJPMRNFBHEA4ICWRHHISTMBST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST/action/storage_attestation","attest_author":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST/action/author_attestation","sign_citation":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST/action/citation_signature","submit_replication":"https://pith.science/pith/JOJPMRNFBHEA4ICWRHHISTMBST/action/replication_record"}},"created_at":"2026-07-05T11:58:25.316664+00:00","updated_at":"2026-07-05T11:58:25.316664+00:00"}