{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FXVV64HSATF7WSPQRYL6E7APLJ","short_pith_number":"pith:FXVV64HS","schema_version":"1.0","canonical_sha256":"2deb5f70f204cbfb49f08e17e27c0f5a4cf8a05d621192c56622f3e5f226420d","source":{"kind":"arxiv","id":"2312.11598","version":3},"attestation_state":"computed","paper":{"title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Yao Mu, Zhixuan Liang","submitted_at":"2023-12-18T18:16:52Z","abstract_excerpt":"Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks requiring multiple sequential skills. We propose SkillDiffuser, an end-to-end hierarchical planning framework integrating interpretable skill learning with conditional diffusion planning to address this problem. At the higher level, the skill abstraction module learns discrete, human-understandable skill representations from visual observations and language instructions. These"},"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":"2312.11598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-18T18:16:52Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"bbf8c7118a85ad15613eb91f5999bcb1a373af950196b19a839e6a7509a48012","abstract_canon_sha256":"188132b8425d5c8b291d5d7f215b7b9dcdaab4b46d6aec693b245462c7ea17cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:35.968628Z","signature_b64":"zff0a3deSRVmp76bs0JB+HjSarIJVUK4aoDK113xPqWsvAg7fxqrw0ZbF12235Cyug5KYauOBnkwKlLrixeXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2deb5f70f204cbfb49f08e17e27c0f5a4cf8a05d621192c56622f3e5f226420d","last_reissued_at":"2026-07-05T08:01:35.968009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:35.968009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Yao Mu, Zhixuan Liang","submitted_at":"2023-12-18T18:16:52Z","abstract_excerpt":"Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks requiring multiple sequential skills. We propose SkillDiffuser, an end-to-end hierarchical planning framework integrating interpretable skill learning with conditional diffusion planning to address this problem. At the higher level, the skill abstraction module learns discrete, human-understandable skill representations from visual observations and language instructions. These"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11598","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/2312.11598/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":"2312.11598","created_at":"2026-07-05T08:01:35.968076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11598v3","created_at":"2026-07-05T08:01:35.968076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11598","created_at":"2026-07-05T08:01:35.968076+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXVV64HSATF7","created_at":"2026-07-05T08:01:35.968076+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXVV64HSATF7WSPQ","created_at":"2026-07-05T08:01:35.968076+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXVV64HS","created_at":"2026-07-05T08:01:35.968076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14125","citing_title":"HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14125","citing_title":"HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ","json":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ.json","graph_json":"https://pith.science/api/pith-number/FXVV64HSATF7WSPQRYL6E7APLJ/graph.json","events_json":"https://pith.science/api/pith-number/FXVV64HSATF7WSPQRYL6E7APLJ/events.json","paper":"https://pith.science/paper/FXVV64HS"},"agent_actions":{"view_html":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ","download_json":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ.json","view_paper":"https://pith.science/paper/FXVV64HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11598&json=true","fetch_graph":"https://pith.science/api/pith-number/FXVV64HSATF7WSPQRYL6E7APLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FXVV64HSATF7WSPQRYL6E7APLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ/action/storage_attestation","attest_author":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ/action/author_attestation","sign_citation":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ/action/citation_signature","submit_replication":"https://pith.science/pith/FXVV64HSATF7WSPQRYL6E7APLJ/action/replication_record"}},"created_at":"2026-07-05T08:01:35.968076+00:00","updated_at":"2026-07-05T08:01:35.968076+00:00"}