{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PE4G2LO5KUP5G7T3WJA3GCHS2E","short_pith_number":"pith:PE4G2LO5","schema_version":"1.0","canonical_sha256":"79386d2ddd551fd37e7bb241b308f2d11b7cc3660a8b525cfff48296205f526a","source":{"kind":"arxiv","id":"2401.08553","version":3},"attestation_state":"computed","paper":{"title":"FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Charles Xu, Fangchen Liu, Jeffrey Wu, Jianlan Luo, Liam Tan, Pieter Abbeel, Sergey Levine, Zipeng Lin","submitted_at":"2024-01-16T18:32:32Z","abstract_excerpt":"In this paper, we propose a real-world benchmark for studying robotic learning in the context of functional manipulation: a robot needs to accomplish complex long-horizon behaviors by composing individual manipulation skills in functionally relevant ways. The core design principles of our Functional Manipulation Benchmark (FMB) emphasize a harmonious balance between complexity and accessibility. Tasks are deliberately scoped to be narrow, ensuring that models and datasets of manageable scale can be utilized effectively to track progress. Simultaneously, they are diverse enough to pose a signif"},"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":"2401.08553","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-01-16T18:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"cc6ba47e8c8747e0e4d969bf2379e8ab4fde85be025a96d84ae4cad3c5865219","abstract_canon_sha256":"db9198a288b7d7731306f20427b2657af75bb7e726ef6ca2ab0f505addcc58fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:15.219980Z","signature_b64":"irbnYop9ssb+PsIZ1THK7RFW74WoDJROn6Kxi6MnAJqdNg8NPEzqSzByge86RaGSx73jDdtD48xWG8uGl87+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79386d2ddd551fd37e7bb241b308f2d11b7cc3660a8b525cfff48296205f526a","last_reissued_at":"2026-07-05T09:02:15.219553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:15.219553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Charles Xu, Fangchen Liu, Jeffrey Wu, Jianlan Luo, Liam Tan, Pieter Abbeel, Sergey Levine, Zipeng Lin","submitted_at":"2024-01-16T18:32:32Z","abstract_excerpt":"In this paper, we propose a real-world benchmark for studying robotic learning in the context of functional manipulation: a robot needs to accomplish complex long-horizon behaviors by composing individual manipulation skills in functionally relevant ways. The core design principles of our Functional Manipulation Benchmark (FMB) emphasize a harmonious balance between complexity and accessibility. Tasks are deliberately scoped to be narrow, ensuring that models and datasets of manageable scale can be utilized effectively to track progress. Simultaneously, they are diverse enough to pose a signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08553","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/2401.08553/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":"2401.08553","created_at":"2026-07-05T09:02:15.219613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08553v3","created_at":"2026-07-05T09:02:15.219613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08553","created_at":"2026-07-05T09:02:15.219613+00:00"},{"alias_kind":"pith_short_12","alias_value":"PE4G2LO5KUP5","created_at":"2026-07-05T09:02:15.219613+00:00"},{"alias_kind":"pith_short_16","alias_value":"PE4G2LO5KUP5G7T3","created_at":"2026-07-05T09:02:15.219613+00:00"},{"alias_kind":"pith_short_8","alias_value":"PE4G2LO5","created_at":"2026-07-05T09:02:15.219613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26428","citing_title":"Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23682","citing_title":"villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19650","citing_title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2405.12213","citing_title":"Octo: An Open-Source Generalist Robot Policy","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E","json":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E.json","graph_json":"https://pith.science/api/pith-number/PE4G2LO5KUP5G7T3WJA3GCHS2E/graph.json","events_json":"https://pith.science/api/pith-number/PE4G2LO5KUP5G7T3WJA3GCHS2E/events.json","paper":"https://pith.science/paper/PE4G2LO5"},"agent_actions":{"view_html":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E","download_json":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E.json","view_paper":"https://pith.science/paper/PE4G2LO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08553&json=true","fetch_graph":"https://pith.science/api/pith-number/PE4G2LO5KUP5G7T3WJA3GCHS2E/graph.json","fetch_events":"https://pith.science/api/pith-number/PE4G2LO5KUP5G7T3WJA3GCHS2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E/action/storage_attestation","attest_author":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E/action/author_attestation","sign_citation":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E/action/citation_signature","submit_replication":"https://pith.science/pith/PE4G2LO5KUP5G7T3WJA3GCHS2E/action/replication_record"}},"created_at":"2026-07-05T09:02:15.219613+00:00","updated_at":"2026-07-05T09:02:15.219613+00:00"}