{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NAJLLYJCPNISP6H6OKVRLVOZTG","short_pith_number":"pith:NAJLLYJC","schema_version":"1.0","canonical_sha256":"6812b5e1227b5127f8fe72ab15d5d9999e6a36b86a627a79cbeaaf57ef90ecbe","source":{"kind":"arxiv","id":"2402.16354","version":2},"attestation_state":"computed","paper":{"title":"Language-guided Skill Learning with Temporal Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Elias Stengel-Eskin, George Konidaris, Haotian Fu, Marc-Alexandre C\\^ot\\'e, Nicolas Le Roux, Pratyusha Sharma, Xingdi Yuan","submitted_at":"2024-02-26T07:19:23Z","abstract_excerpt":"We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate tha"},"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":"2402.16354","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T07:19:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b47e0fa590c90300c1614c182a64b68697596622c0e8b7103f360c9e29073c45","abstract_canon_sha256":"a1c25dec6efe2577500baef602ed6d73a05435cd89881874950c34a3e12cef96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:18.687869Z","signature_b64":"OMOIDEJfLgYqjtoqLX9D2qORnzkH5qrHiL/ZC07MWuPTvvhj1OSu+qJDiNtITbItGqRTX7VkKYlMI1o50QSPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6812b5e1227b5127f8fe72ab15d5d9999e6a36b86a627a79cbeaaf57ef90ecbe","last_reissued_at":"2026-07-05T08:23:18.687370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:18.687370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-guided Skill Learning with Temporal Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Elias Stengel-Eskin, George Konidaris, Haotian Fu, Marc-Alexandre C\\^ot\\'e, Nicolas Le Roux, Pratyusha Sharma, Xingdi Yuan","submitted_at":"2024-02-26T07:19:23Z","abstract_excerpt":"We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16354","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/2402.16354/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":"2402.16354","created_at":"2026-07-05T08:23:18.687433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16354v2","created_at":"2026-07-05T08:23:18.687433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16354","created_at":"2026-07-05T08:23:18.687433+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAJLLYJCPNIS","created_at":"2026-07-05T08:23:18.687433+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAJLLYJCPNISP6H6","created_at":"2026-07-05T08:23:18.687433+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAJLLYJC","created_at":"2026-07-05T08:23:18.687433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03598","citing_title":"PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG","json":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG.json","graph_json":"https://pith.science/api/pith-number/NAJLLYJCPNISP6H6OKVRLVOZTG/graph.json","events_json":"https://pith.science/api/pith-number/NAJLLYJCPNISP6H6OKVRLVOZTG/events.json","paper":"https://pith.science/paper/NAJLLYJC"},"agent_actions":{"view_html":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG","download_json":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG.json","view_paper":"https://pith.science/paper/NAJLLYJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16354&json=true","fetch_graph":"https://pith.science/api/pith-number/NAJLLYJCPNISP6H6OKVRLVOZTG/graph.json","fetch_events":"https://pith.science/api/pith-number/NAJLLYJCPNISP6H6OKVRLVOZTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG/action/storage_attestation","attest_author":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG/action/author_attestation","sign_citation":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG/action/citation_signature","submit_replication":"https://pith.science/pith/NAJLLYJCPNISP6H6OKVRLVOZTG/action/replication_record"}},"created_at":"2026-07-05T08:23:18.687433+00:00","updated_at":"2026-07-05T08:23:18.687433+00:00"}