{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36FEO7O7CEZZ45LBJUKYIXSKMR","short_pith_number":"pith:36FEO7O7","schema_version":"1.0","canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","source":{"kind":"arxiv","id":"2505.19337","version":2},"attestation_state":"computed","paper":{"title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Kevin Li, Marinka Zitnik","submitted_at":"2025-05-25T22:00:38Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning methods have shown promise for reach-avoid tasks, where an agent must reach a target state while avoiding undesirable regions of the state space. Existing approaches typically encode avoid-region information into an augmented state space and cost function, which prevents flexible, dynamic specification of novel avoid-region information at evaluation time. They also rely heavily on well-designed reward and cost functions, limiting scalability to complex or poorly structured environments. We introduce RADT, a decision transformer model for offline,"},"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":"2505.19337","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T22:00:38Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"02a2774f81b7ae00ba899e7abfac5dcad59dbbb0960ecf4543693af91107c79f","abstract_canon_sha256":"a9ba916d9bc1494e80719d7f98a62a6eaf8b7196da540d22334aaea540898e81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:09.977728Z","signature_b64":"59PApaqTH6cWBTfC5vrn2DdsrY95L7FemhPTYbPeZK+BCDHqh4nC3wG+MzkhaRAcHQRH7O5IYBxjEYTj5ft5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","last_reissued_at":"2026-07-05T11:10:09.977105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:09.977105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Kevin Li, Marinka Zitnik","submitted_at":"2025-05-25T22:00:38Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning methods have shown promise for reach-avoid tasks, where an agent must reach a target state while avoiding undesirable regions of the state space. Existing approaches typically encode avoid-region information into an augmented state space and cost function, which prevents flexible, dynamic specification of novel avoid-region information at evaluation time. They also rely heavily on well-designed reward and cost functions, limiting scalability to complex or poorly structured environments. We introduce RADT, a decision transformer model for offline,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19337","kind":"arxiv","version":2},"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/2505.19337/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":"2505.19337","created_at":"2026-07-05T11:10:09.977176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19337v2","created_at":"2026-07-05T11:10:09.977176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19337","created_at":"2026-07-05T11:10:09.977176+00:00"},{"alias_kind":"pith_short_12","alias_value":"36FEO7O7CEZZ","created_at":"2026-07-05T11:10:09.977176+00:00"},{"alias_kind":"pith_short_16","alias_value":"36FEO7O7CEZZ45LB","created_at":"2026-07-05T11:10:09.977176+00:00"},{"alias_kind":"pith_short_8","alias_value":"36FEO7O7","created_at":"2026-07-05T11:10:09.977176+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/36FEO7O7CEZZ45LBJUKYIXSKMR","json":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR.json","graph_json":"https://pith.science/api/pith-number/36FEO7O7CEZZ45LBJUKYIXSKMR/graph.json","events_json":"https://pith.science/api/pith-number/36FEO7O7CEZZ45LBJUKYIXSKMR/events.json","paper":"https://pith.science/paper/36FEO7O7"},"agent_actions":{"view_html":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR","download_json":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR.json","view_paper":"https://pith.science/paper/36FEO7O7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19337&json=true","fetch_graph":"https://pith.science/api/pith-number/36FEO7O7CEZZ45LBJUKYIXSKMR/graph.json","fetch_events":"https://pith.science/api/pith-number/36FEO7O7CEZZ45LBJUKYIXSKMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/action/storage_attestation","attest_author":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/action/author_attestation","sign_citation":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/action/citation_signature","submit_replication":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/action/replication_record"}},"created_at":"2026-07-05T11:10:09.977176+00:00","updated_at":"2026-07-05T11:10:09.977176+00:00"}