{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A6B2J4DICMDHYDTKYRR33XX6F6","short_pith_number":"pith:A6B2J4DI","schema_version":"1.0","canonical_sha256":"0783a4f06813067c0e6ac463bddefe2faee362bcaa70b4e9bb17324cca39e824","source":{"kind":"arxiv","id":"2503.07087","version":1},"attestation_state":"computed","paper":{"title":"iManip: Skill-Incremental Learning for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jia-Feng Cai, Wei-Shi Zheng, Xiao-Ming Wu, Yi-Lin Wei, Yu-Ming Tang, Zexin Zheng","submitted_at":"2025-03-10T09:10:05Z","abstract_excerpt":"The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the pr"},"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":"2503.07087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-10T09:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"38cef8de364caed8eba3c54cb171c161b992b3f004eb76a44ac3bae87586f9ed","abstract_canon_sha256":"29f6925dbe5ccbcaf5fe5e08767e1bd9e64142c167d9eb5d266237ebee2631df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:49.534334Z","signature_b64":"PgdBaOPIHTtizUHPjMt+HHh50j/4uqtcPy7y16Z4rYJUFRmslih9RkArLDE1k2ubRH5BuvHxw6t9nzhV+2X9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0783a4f06813067c0e6ac463bddefe2faee362bcaa70b4e9bb17324cca39e824","last_reissued_at":"2026-07-05T10:27:49.533650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:49.533650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iManip: Skill-Incremental Learning for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jia-Feng Cai, Wei-Shi Zheng, Xiao-Ming Wu, Yi-Lin Wei, Yu-Ming Tang, Zexin Zheng","submitted_at":"2025-03-10T09:10:05Z","abstract_excerpt":"The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07087","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/2503.07087/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":"2503.07087","created_at":"2026-07-05T10:27:49.533740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07087v1","created_at":"2026-07-05T10:27:49.533740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07087","created_at":"2026-07-05T10:27:49.533740+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6B2J4DICMDH","created_at":"2026-07-05T10:27:49.533740+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6B2J4DICMDHYDTK","created_at":"2026-07-05T10:27:49.533740+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6B2J4DI","created_at":"2026-07-05T10:27:49.533740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13045","citing_title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","ref_index":264,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6","json":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6.json","graph_json":"https://pith.science/api/pith-number/A6B2J4DICMDHYDTKYRR33XX6F6/graph.json","events_json":"https://pith.science/api/pith-number/A6B2J4DICMDHYDTKYRR33XX6F6/events.json","paper":"https://pith.science/paper/A6B2J4DI"},"agent_actions":{"view_html":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6","download_json":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6.json","view_paper":"https://pith.science/paper/A6B2J4DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07087&json=true","fetch_graph":"https://pith.science/api/pith-number/A6B2J4DICMDHYDTKYRR33XX6F6/graph.json","fetch_events":"https://pith.science/api/pith-number/A6B2J4DICMDHYDTKYRR33XX6F6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6/action/storage_attestation","attest_author":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6/action/author_attestation","sign_citation":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6/action/citation_signature","submit_replication":"https://pith.science/pith/A6B2J4DICMDHYDTKYRR33XX6F6/action/replication_record"}},"created_at":"2026-07-05T10:27:49.533740+00:00","updated_at":"2026-07-05T10:27:49.533740+00:00"}