{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FO6MWVL3CQLQUVRUTLWRLJQY4E","short_pith_number":"pith:FO6MWVL3","schema_version":"1.0","canonical_sha256":"2bbccb557b14170a56349aed15a618e10748f251dab7f04a3b6c0c76e6c37860","source":{"kind":"arxiv","id":"2501.18848","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ryota Yamashina, Takamitsu Matsubara, Wataru Hatanaka","submitted_at":"2025-01-31T02:02:40Z","abstract_excerpt":"Symbolic task representation is a powerful tool for encoding human instructions and domain knowledge. Such instructions guide robots to accomplish diverse objectives and meet constraints through reinforcement learning (RL). Most existing methods are based on fixed mappings from environmental states to symbols. However, in inspection tasks, where equipment conditions must be evaluated from multiple perspectives to avoid errors of oversight, robots must fulfill the same symbol from different states. To help robots respond to flexible symbol mapping, we propose representing symbols and their mapp"},"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":"2501.18848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-31T02:02:40Z","cross_cats_sorted":[],"title_canon_sha256":"2ba895facc9d5b17fde814c79cec376c0fa3d9a83338072305d5c4f0a98d5bc0","abstract_canon_sha256":"28d97e889f45e7806784087550d2e3195f68cbff2a0bde0aec5b24b809218aaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:52.722775Z","signature_b64":"GwmlONOXoGgMlWNoim65VYD5iGlhdHoSXgnBGUmiqciuytp5XaPBVYvsh7exyxHwzkXLDoQvUD8lwjEJXU1/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bbccb557b14170a56349aed15a618e10748f251dab7f04a3b6c0c76e6c37860","last_reissued_at":"2026-07-05T10:07:52.722263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:52.722263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ryota Yamashina, Takamitsu Matsubara, Wataru Hatanaka","submitted_at":"2025-01-31T02:02:40Z","abstract_excerpt":"Symbolic task representation is a powerful tool for encoding human instructions and domain knowledge. Such instructions guide robots to accomplish diverse objectives and meet constraints through reinforcement learning (RL). Most existing methods are based on fixed mappings from environmental states to symbols. However, in inspection tasks, where equipment conditions must be evaluated from multiple perspectives to avoid errors of oversight, robots must fulfill the same symbol from different states. To help robots respond to flexible symbol mapping, we propose representing symbols and their mapp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18848","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/2501.18848/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":"2501.18848","created_at":"2026-07-05T10:07:52.722334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18848v1","created_at":"2026-07-05T10:07:52.722334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18848","created_at":"2026-07-05T10:07:52.722334+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO6MWVL3CQLQ","created_at":"2026-07-05T10:07:52.722334+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO6MWVL3CQLQUVRU","created_at":"2026-07-05T10:07:52.722334+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO6MWVL3","created_at":"2026-07-05T10:07:52.722334+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/FO6MWVL3CQLQUVRUTLWRLJQY4E","json":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E.json","graph_json":"https://pith.science/api/pith-number/FO6MWVL3CQLQUVRUTLWRLJQY4E/graph.json","events_json":"https://pith.science/api/pith-number/FO6MWVL3CQLQUVRUTLWRLJQY4E/events.json","paper":"https://pith.science/paper/FO6MWVL3"},"agent_actions":{"view_html":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E","download_json":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E.json","view_paper":"https://pith.science/paper/FO6MWVL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18848&json=true","fetch_graph":"https://pith.science/api/pith-number/FO6MWVL3CQLQUVRUTLWRLJQY4E/graph.json","fetch_events":"https://pith.science/api/pith-number/FO6MWVL3CQLQUVRUTLWRLJQY4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E/action/storage_attestation","attest_author":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E/action/author_attestation","sign_citation":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E/action/citation_signature","submit_replication":"https://pith.science/pith/FO6MWVL3CQLQUVRUTLWRLJQY4E/action/replication_record"}},"created_at":"2026-07-05T10:07:52.722334+00:00","updated_at":"2026-07-05T10:07:52.722334+00:00"}