{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VPIIIN4P2Q2KFF37QE75BTU5YI","short_pith_number":"pith:VPIIIN4P","schema_version":"1.0","canonical_sha256":"abd084378fd434a2977f813fd0ce9dc22e1c5e9cc9701ad27f53a7a081f783c1","source":{"kind":"arxiv","id":"2506.05702","version":1},"attestation_state":"computed","paper":{"title":"Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaofan Pan, Fan Min, Jiafen Liu, Linbo Xiong, Wei Wei, Xin Yang, Yanhua Li","submitted_at":"2025-06-06T03:07:30Z","abstract_excerpt":"Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that the agent's capabilities remain static within dynamic environments, which doesn't reflect real-world scenarios where capabilities dynamically change. This paper introduces a new and realistic problem: Continual Learning with Dynamic Capabilities (CL-DC), posing a significant challenge for CL agents: How can policy generalization across different action spac"},"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":"2506.05702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T03:07:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ade408fac76fe9167add5995ac06f847cf9a52e5c0bfc97d933039a748a9818b","abstract_canon_sha256":"0cd9b2e1d3111a7d5d4ab7c72ee6d817cec674a42a63e513727c7d59a4f00c59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:08.282538Z","signature_b64":"0JBFgU626g+DS97GMzqs/RRbf0npEmy82mMJ3K5AarvkKyOcdYU4NCES8f5Qme6LW+AFRsoekeqp2Lu0SC3LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abd084378fd434a2977f813fd0ce9dc22e1c5e9cc9701ad27f53a7a081f783c1","last_reissued_at":"2026-07-05T11:17:08.281912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:08.281912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaofan Pan, Fan Min, Jiafen Liu, Linbo Xiong, Wei Wei, Xin Yang, Yanhua Li","submitted_at":"2025-06-06T03:07:30Z","abstract_excerpt":"Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that the agent's capabilities remain static within dynamic environments, which doesn't reflect real-world scenarios where capabilities dynamically change. This paper introduces a new and realistic problem: Continual Learning with Dynamic Capabilities (CL-DC), posing a significant challenge for CL agents: How can policy generalization across different action spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05702","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/2506.05702/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":"2506.05702","created_at":"2026-07-05T11:17:08.281992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05702v1","created_at":"2026-07-05T11:17:08.281992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05702","created_at":"2026-07-05T11:17:08.281992+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPIIIN4P2Q2K","created_at":"2026-07-05T11:17:08.281992+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPIIIN4P2Q2KFF37","created_at":"2026-07-05T11:17:08.281992+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPIIIN4P","created_at":"2026-07-05T11:17:08.281992+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/VPIIIN4P2Q2KFF37QE75BTU5YI","json":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI.json","graph_json":"https://pith.science/api/pith-number/VPIIIN4P2Q2KFF37QE75BTU5YI/graph.json","events_json":"https://pith.science/api/pith-number/VPIIIN4P2Q2KFF37QE75BTU5YI/events.json","paper":"https://pith.science/paper/VPIIIN4P"},"agent_actions":{"view_html":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI","download_json":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI.json","view_paper":"https://pith.science/paper/VPIIIN4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05702&json=true","fetch_graph":"https://pith.science/api/pith-number/VPIIIN4P2Q2KFF37QE75BTU5YI/graph.json","fetch_events":"https://pith.science/api/pith-number/VPIIIN4P2Q2KFF37QE75BTU5YI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI/action/storage_attestation","attest_author":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI/action/author_attestation","sign_citation":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI/action/citation_signature","submit_replication":"https://pith.science/pith/VPIIIN4P2Q2KFF37QE75BTU5YI/action/replication_record"}},"created_at":"2026-07-05T11:17:08.281992+00:00","updated_at":"2026-07-05T11:17:08.281992+00:00"}