{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DOYPZTPJR7KVOXBPRW3JXGJEWJ","short_pith_number":"pith:DOYPZTPJ","schema_version":"1.0","canonical_sha256":"1bb0fccde98fd5575c2f8db69b9924b243ec6a388e102c73dfdfbaea773ad8ff","source":{"kind":"arxiv","id":"2606.31260","version":1},"attestation_state":"computed","paper":{"title":"Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lujie Yin, Xiangli Shi, Xiaomeng Zhu, Ye Tian, Yuchun Guo, Yufei Huang, Yuxuan Zhou, Ziyang Sun","submitted_at":"2026-06-30T07:37:21Z","abstract_excerpt":"Embodied task planning asks an agent to turn a natural-language instruction into an executable sequence of actions in a physical scene, and is a building block for household, assistive, and service robots. Recent prompting-based and reinforcement-learning planners generate fluent action text but lack a cheap deterministic check that the produced plan is valid in the target world, while high-fidelity simulation is too slow to serve as an inner-loop training signal. The general problem is therefore how to obtain verifiable supervision and rewards for embodied planners without relying on string-l"},"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":"2606.31260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T07:37:21Z","cross_cats_sorted":[],"title_canon_sha256":"a75942522cfb9538b990974cffe0a86fa5d4f2f9e249f1be38c2acdef0de2fb9","abstract_canon_sha256":"a6bd943b5b4603fe489ccbb9d3da143273c15217eb15b138b1d17eeba86320a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:57.419022Z","signature_b64":"Hhpuxl9TN5hD+YcS55DEV+Fp6q74Sw4ElOGR+csFk2Z0DFZrAJcP41veh3dcuntw5PRzssV+FAeROLWBI21VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb0fccde98fd5575c2f8db69b9924b243ec6a388e102c73dfdfbaea773ad8ff","last_reissued_at":"2026-07-01T01:17:57.418608Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:57.418608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lujie Yin, Xiangli Shi, Xiaomeng Zhu, Ye Tian, Yuchun Guo, Yufei Huang, Yuxuan Zhou, Ziyang Sun","submitted_at":"2026-06-30T07:37:21Z","abstract_excerpt":"Embodied task planning asks an agent to turn a natural-language instruction into an executable sequence of actions in a physical scene, and is a building block for household, assistive, and service robots. Recent prompting-based and reinforcement-learning planners generate fluent action text but lack a cheap deterministic check that the produced plan is valid in the target world, while high-fidelity simulation is too slow to serve as an inner-loop training signal. The general problem is therefore how to obtain verifiable supervision and rewards for embodied planners without relying on string-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31260","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/2606.31260/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":"2606.31260","created_at":"2026-07-01T01:17:57.418668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31260v1","created_at":"2026-07-01T01:17:57.418668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31260","created_at":"2026-07-01T01:17:57.418668+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOYPZTPJR7KV","created_at":"2026-07-01T01:17:57.418668+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOYPZTPJR7KVOXBP","created_at":"2026-07-01T01:17:57.418668+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOYPZTPJ","created_at":"2026-07-01T01:17:57.418668+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/DOYPZTPJR7KVOXBPRW3JXGJEWJ","json":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ.json","graph_json":"https://pith.science/api/pith-number/DOYPZTPJR7KVOXBPRW3JXGJEWJ/graph.json","events_json":"https://pith.science/api/pith-number/DOYPZTPJR7KVOXBPRW3JXGJEWJ/events.json","paper":"https://pith.science/paper/DOYPZTPJ"},"agent_actions":{"view_html":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ","download_json":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ.json","view_paper":"https://pith.science/paper/DOYPZTPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31260&json=true","fetch_graph":"https://pith.science/api/pith-number/DOYPZTPJR7KVOXBPRW3JXGJEWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DOYPZTPJR7KVOXBPRW3JXGJEWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ/action/storage_attestation","attest_author":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ/action/author_attestation","sign_citation":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ/action/citation_signature","submit_replication":"https://pith.science/pith/DOYPZTPJR7KVOXBPRW3JXGJEWJ/action/replication_record"}},"created_at":"2026-07-01T01:17:57.418668+00:00","updated_at":"2026-07-01T01:17:57.418668+00:00"}