{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6IV7O7VVNORI6JK4TN7YZ6VKX","short_pith_number":"pith:P6IV7O7V","schema_version":"1.0","canonical_sha256":"7f915fbbf5ab5d14792ae4dbfc67d555fd50e8ef8fc2c9ab7bb02541250ee54f","source":{"kind":"arxiv","id":"2508.17547","version":1},"attestation_state":"computed","paper":{"title":"LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hao Su, Jiawei Fu, Weikang Wan, Xiaodi Yuan, Yifeng Zhu","submitted_at":"2025-08-24T22:57:16Z","abstract_excerpt":"Developing robotic systems capable of robustly executing long-horizon manipulation tasks with human-level dexterity is challenging, as such tasks require both physical dexterity and seamless sequencing of manipulation skills while robustly handling environment variations. While imitation learning offers a promising approach, acquiring comprehensive datasets is resource-intensive. In this work, we propose a learning framework and system LodeStar that automatically decomposes task demonstrations into semantically meaningful skills using off-the-shelf foundation models, and generates diverse synt"},"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":"2508.17547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-24T22:57:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac206685d243a6fd0f8af53126f6289112cb14116ca8c042fafe51693ed83c44","abstract_canon_sha256":"504ea56099731b696f46bca8164819efbc7f129b746e79e51e203cd8a16cd055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:43.303235Z","signature_b64":"JMCnSFXVwlXb6A3+Va7KHRL6V4vqnhgIZ8iPQSV89SC35Q5+hhonFubh25qkapy3kOYb7S0yP9SVYOGBkmzXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f915fbbf5ab5d14792ae4dbfc67d555fd50e8ef8fc2c9ab7bb02541250ee54f","last_reissued_at":"2026-07-05T11:58:43.302658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:43.302658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hao Su, Jiawei Fu, Weikang Wan, Xiaodi Yuan, Yifeng Zhu","submitted_at":"2025-08-24T22:57:16Z","abstract_excerpt":"Developing robotic systems capable of robustly executing long-horizon manipulation tasks with human-level dexterity is challenging, as such tasks require both physical dexterity and seamless sequencing of manipulation skills while robustly handling environment variations. While imitation learning offers a promising approach, acquiring comprehensive datasets is resource-intensive. In this work, we propose a learning framework and system LodeStar that automatically decomposes task demonstrations into semantically meaningful skills using off-the-shelf foundation models, and generates diverse synt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17547","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/2508.17547/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":"2508.17547","created_at":"2026-07-05T11:58:43.302729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17547v1","created_at":"2026-07-05T11:58:43.302729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17547","created_at":"2026-07-05T11:58:43.302729+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6IV7O7VVNOR","created_at":"2026-07-05T11:58:43.302729+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6IV7O7VVNORI6JK","created_at":"2026-07-05T11:58:43.302729+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6IV7O7V","created_at":"2026-07-05T11:58:43.302729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX","json":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX.json","graph_json":"https://pith.science/api/pith-number/P6IV7O7VVNORI6JK4TN7YZ6VKX/graph.json","events_json":"https://pith.science/api/pith-number/P6IV7O7VVNORI6JK4TN7YZ6VKX/events.json","paper":"https://pith.science/paper/P6IV7O7V"},"agent_actions":{"view_html":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX","download_json":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX.json","view_paper":"https://pith.science/paper/P6IV7O7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17547&json=true","fetch_graph":"https://pith.science/api/pith-number/P6IV7O7VVNORI6JK4TN7YZ6VKX/graph.json","fetch_events":"https://pith.science/api/pith-number/P6IV7O7VVNORI6JK4TN7YZ6VKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX/action/storage_attestation","attest_author":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX/action/author_attestation","sign_citation":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX/action/citation_signature","submit_replication":"https://pith.science/pith/P6IV7O7VVNORI6JK4TN7YZ6VKX/action/replication_record"}},"created_at":"2026-07-05T11:58:43.302729+00:00","updated_at":"2026-07-05T11:58:43.302729+00:00"}