{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMQ775VCKUUWQY2UGI6FFSKCR6","short_pith_number":"pith:TMQ775VC","schema_version":"1.0","canonical_sha256":"9b21fff6a25529686354323c52c9428f93efdcaa5b1075b07901e5652874b2f1","source":{"kind":"arxiv","id":"2504.14805","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jinwoo Choi, Seung-Woo Seo","submitted_at":"2025-04-21T02:11:39Z","abstract_excerpt":"Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into higher-level behaviors. However, current approaches often fail to recognize semantically similar behaviors as the same skill and use fixed skill lengths, limiting flexibility and generalization. To address this, we propose Dynamic Contrastive Skill Learning (DCSL), a novel framework that redefines skill representation and learning. DCSL introduces three key ideas: "},"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":"2504.14805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-21T02:11:39Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"af2f77efe60cd335101df1a6f983c74b21337966472867dab05445964cb47722","abstract_canon_sha256":"8c7efb6e3abc2b0cc65aa7fdee31acebb83cd54e1d3e698b6924e65d46ab8d7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:50.729148Z","signature_b64":"ArzRdIj7go78u+rYuvJzarTs0EO8aMecQwgJ6k6gFEPXPhPZtMrZsrnaAPai/YrPdtGNMYUCrvqsDffA++M8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b21fff6a25529686354323c52c9428f93efdcaa5b1075b07901e5652874b2f1","last_reissued_at":"2026-07-05T10:51:50.728609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:50.728609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jinwoo Choi, Seung-Woo Seo","submitted_at":"2025-04-21T02:11:39Z","abstract_excerpt":"Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into higher-level behaviors. However, current approaches often fail to recognize semantically similar behaviors as the same skill and use fixed skill lengths, limiting flexibility and generalization. To address this, we propose Dynamic Contrastive Skill Learning (DCSL), a novel framework that redefines skill representation and learning. DCSL introduces three key ideas: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14805","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/2504.14805/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":"2504.14805","created_at":"2026-07-05T10:51:50.728668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14805v1","created_at":"2026-07-05T10:51:50.728668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14805","created_at":"2026-07-05T10:51:50.728668+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMQ775VCKUUW","created_at":"2026-07-05T10:51:50.728668+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMQ775VCKUUWQY2U","created_at":"2026-07-05T10:51:50.728668+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMQ775VC","created_at":"2026-07-05T10:51:50.728668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6","json":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6.json","graph_json":"https://pith.science/api/pith-number/TMQ775VCKUUWQY2UGI6FFSKCR6/graph.json","events_json":"https://pith.science/api/pith-number/TMQ775VCKUUWQY2UGI6FFSKCR6/events.json","paper":"https://pith.science/paper/TMQ775VC"},"agent_actions":{"view_html":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6","download_json":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6.json","view_paper":"https://pith.science/paper/TMQ775VC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14805&json=true","fetch_graph":"https://pith.science/api/pith-number/TMQ775VCKUUWQY2UGI6FFSKCR6/graph.json","fetch_events":"https://pith.science/api/pith-number/TMQ775VCKUUWQY2UGI6FFSKCR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6/action/storage_attestation","attest_author":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6/action/author_attestation","sign_citation":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6/action/citation_signature","submit_replication":"https://pith.science/pith/TMQ775VCKUUWQY2UGI6FFSKCR6/action/replication_record"}},"created_at":"2026-07-05T10:51:50.728668+00:00","updated_at":"2026-07-05T10:51:50.728668+00:00"}