{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G7FALOEE2SJ7BJ3RLHMZUXS2C3","short_pith_number":"pith:G7FALOEE","schema_version":"1.0","canonical_sha256":"37ca05b884d493f0a77159d99a5e5a16d5a91c4b7be2cab2a61f1f22ce90795a","source":{"kind":"arxiv","id":"2606.12890","version":1},"attestation_state":"computed","paper":{"title":"Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aryan Naveen, Haitong Ma, Haldun Balim, Na Li","submitted_at":"2026-06-11T04:33:03Z","abstract_excerpt":"Reinforcement learning has achieved remarkable success in learning complex control policies, yet its applicability remains limited due to sample inefficiency and poor generalization across tasks. In this work, we propose RepMT-SAC, a framework for multi-task RL that enables efficient knowledge sharing and robust transfer to new tasks. RepMT-SAC uses spectral MDP decomposition to capture transferable dynamics, structuring the value function into a task-agnostic core with a minimal task-specific adjustment. This design allows for strong zero-shot performance on in-distribution tasks and rapid fe"},"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":"2606.12890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-11T04:33:03Z","cross_cats_sorted":[],"title_canon_sha256":"4ba3cbb15172efd533b4c73ba21db05b561f84137feee67193a9287533c8ae3a","abstract_canon_sha256":"a07930836929e5273ae1e8cbdf0f1ac808b083e5a4deff3c6ecc1d588f4deb93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:57.129262Z","signature_b64":"fPpP1MawIlKa344jUPNF57gODNBvW/Yisi3jaiDXQ2ztnsk93R55Ms9X63G72yM6qxrMBJa9NbKRY7ndXIuoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ca05b884d493f0a77159d99a5e5a16d5a91c4b7be2cab2a61f1f22ce90795a","last_reissued_at":"2026-06-12T01:08:57.128271Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:57.128271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aryan Naveen, Haitong Ma, Haldun Balim, Na Li","submitted_at":"2026-06-11T04:33:03Z","abstract_excerpt":"Reinforcement learning has achieved remarkable success in learning complex control policies, yet its applicability remains limited due to sample inefficiency and poor generalization across tasks. In this work, we propose RepMT-SAC, a framework for multi-task RL that enables efficient knowledge sharing and robust transfer to new tasks. RepMT-SAC uses spectral MDP decomposition to capture transferable dynamics, structuring the value function into a task-agnostic core with a minimal task-specific adjustment. This design allows for strong zero-shot performance on in-distribution tasks and rapid fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12890","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/2606.12890/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":"2606.12890","created_at":"2026-06-12T01:08:57.128453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12890v1","created_at":"2026-06-12T01:08:57.128453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12890","created_at":"2026-06-12T01:08:57.128453+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7FALOEE2SJ7","created_at":"2026-06-12T01:08:57.128453+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7FALOEE2SJ7BJ3R","created_at":"2026-06-12T01:08:57.128453+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7FALOEE","created_at":"2026-06-12T01:08:57.128453+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/G7FALOEE2SJ7BJ3RLHMZUXS2C3","json":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3.json","graph_json":"https://pith.science/api/pith-number/G7FALOEE2SJ7BJ3RLHMZUXS2C3/graph.json","events_json":"https://pith.science/api/pith-number/G7FALOEE2SJ7BJ3RLHMZUXS2C3/events.json","paper":"https://pith.science/paper/G7FALOEE"},"agent_actions":{"view_html":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3","download_json":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3.json","view_paper":"https://pith.science/paper/G7FALOEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12890&json=true","fetch_graph":"https://pith.science/api/pith-number/G7FALOEE2SJ7BJ3RLHMZUXS2C3/graph.json","fetch_events":"https://pith.science/api/pith-number/G7FALOEE2SJ7BJ3RLHMZUXS2C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3/action/storage_attestation","attest_author":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3/action/author_attestation","sign_citation":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3/action/citation_signature","submit_replication":"https://pith.science/pith/G7FALOEE2SJ7BJ3RLHMZUXS2C3/action/replication_record"}},"created_at":"2026-06-12T01:08:57.128453+00:00","updated_at":"2026-06-12T01:08:57.128453+00:00"}