{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:36FEO7O7CEZZ45LBJUKYIXSKMR","short_pith_number":"pith:36FEO7O7","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"},"canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","source":{"kind":"arxiv","id":"2505.19337","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19337","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19337v2","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19337","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_12","alias_value":"36FEO7O7CEZZ","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_16","alias_value":"36FEO7O7CEZZ45LB","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_8","alias_value":"36FEO7O7","created_at":"2026-07-05T11:10:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:36FEO7O7CEZZ45LBJUKYIXSKMR","target":"record","payload":{"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"},"canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","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"},"source_kind":"arxiv","source_id":"2505.19337","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jW8R3mOXeX68ogT/Z8MPyrw3vDxRVh60vtiH6txaNOhfzq8YhnlnV0t0l8SXYKPNqYL5KifEGC5nXyD26B5iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:54:39.634870Z"},"content_sha256":"6863eb0390a2609f3511d238ad8e38ca597dca4d8c53dbc26df0ce898545f274","schema_version":"1.0","event_id":"sha256:6863eb0390a2609f3511d238ad8e38ca597dca4d8c53dbc26df0ce898545f274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:36FEO7O7CEZZ45LBJUKYIXSKMR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YaXK3D4wzROuo5iYe0bABG0WmT/vJusaP6ayPEDPWeMFuGcY+RzRZ7xZSNjbWkdDuehxfDFM4ebmHHLkthBVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:54:39.636750Z"},"content_sha256":"9c137141b48a8c9913d7798a30fd104b79d799e0014d91a30d052923b42502b9","schema_version":"1.0","event_id":"sha256:9c137141b48a8c9913d7798a30fd104b79d799e0014d91a30d052923b42502b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/bundle.json","state_url":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:54:39Z","links":{"resolver":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR","bundle":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/bundle.json","state":"https://pith.science/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36FEO7O7CEZZ45LBJUKYIXSKMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:36FEO7O7CEZZ45LBJUKYIXSKMR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a9ba916d9bc1494e80719d7f98a62a6eaf8b7196da540d22334aaea540898e81","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T22:00:38Z","title_canon_sha256":"02a2774f81b7ae00ba899e7abfac5dcad59dbbb0960ecf4543693af91107c79f"},"schema_version":"1.0","source":{"id":"2505.19337","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19337","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19337v2","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19337","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_12","alias_value":"36FEO7O7CEZZ","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_16","alias_value":"36FEO7O7CEZZ45LB","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_8","alias_value":"36FEO7O7","created_at":"2026-07-05T11:10:09Z"}],"graph_snapshots":[{"event_id":"sha256:9c137141b48a8c9913d7798a30fd104b79d799e0014d91a30d052923b42502b9","target":"graph","created_at":"2026-07-05T11:10:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.19337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Kevin Li, Marinka Zitnik","cross_cats":["cs.AI","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T22:00:38Z","title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19337","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6863eb0390a2609f3511d238ad8e38ca597dca4d8c53dbc26df0ce898545f274","target":"record","created_at":"2026-07-05T11:10:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a9ba916d9bc1494e80719d7f98a62a6eaf8b7196da540d22334aaea540898e81","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T22:00:38Z","title_canon_sha256":"02a2774f81b7ae00ba899e7abfac5dcad59dbbb0960ecf4543693af91107c79f"},"schema_version":"1.0","source":{"id":"2505.19337","kind":"arxiv","version":2}},"canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df8a477ddf11339e75614d15845e4a646b097d5a274bc3f75b276b1efe02daf6","first_computed_at":"2026-07-05T11:10:09.977105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:09.977105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"59PApaqTH6cWBTfC5vrn2DdsrY95L7FemhPTYbPeZK+BCDHqh4nC3wG+MzkhaRAcHQRH7O5IYBxjEYTj5ft5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:09.977728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19337","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6863eb0390a2609f3511d238ad8e38ca597dca4d8c53dbc26df0ce898545f274","sha256:9c137141b48a8c9913d7798a30fd104b79d799e0014d91a30d052923b42502b9"],"state_sha256":"d91eb95b0d1446fb0104e8928587d8e04c958d0020b93f67a49df39f2deb7043"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYvay/5IsS/LFodZ1dJARJ25UU+ihAM5kOYa5JZgat70MP0KHQxrZISZ3vsWFyuPOb/90iQFSW7t4tF97uyWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:54:39.647147Z","bundle_sha256":"f409a6c720bb68eff437bf94e0fda3d8e43df9ff04d0ab1763586655a3b44d2f"}}