{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EMUOC4JWJDPJJTUEQ2BUMRDKNI","short_pith_number":"pith:EMUOC4JW","schema_version":"1.0","canonical_sha256":"2328e1713648de94ce84868346446a6a3f99bc737ef03c330d603f5777c84047","source":{"kind":"arxiv","id":"2110.09461","version":2},"attestation_state":"computed","paper":{"title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Borja G. Le\\'on, Francesco Belardinelli, Murray Shanahan","submitted_at":"2021-10-18T16:53:31Z","abstract_excerpt":"We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the agent's neural architecture is a key feature when DRL agents are learning to solve OOD tasks in TL. Yet, the studies on this topic are still in their infancy. In this work, we propose a new deep learning configuration with inductive biases that lead agents to generate latent representations of their current goal, yielding a stronger generalization perform"},"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":"2110.09461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-18T16:53:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc44ac7e8df77f6de16d5ae6354fd2f22eb55819d1dbb50566a13fadc02eceb1","abstract_canon_sha256":"ab15ca79e73a2e263fd8608027e33bbb54fde67d7bd53fa3d0ee8ffc63d2406f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:41.337173Z","signature_b64":"DvuQnBxvXXTbWHL783bxOCB1kC5NxGSSsDQlDfdsRQ5izBt8/PHhugQfH4ZLzVt3bfMP8t7HOHENS1Zx/ABNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2328e1713648de94ce84868346446a6a3f99bc737ef03c330d603f5777c84047","last_reissued_at":"2026-07-05T03:59:41.336768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:41.336768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Borja G. Le\\'on, Francesco Belardinelli, Murray Shanahan","submitted_at":"2021-10-18T16:53:31Z","abstract_excerpt":"We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the agent's neural architecture is a key feature when DRL agents are learning to solve OOD tasks in TL. Yet, the studies on this topic are still in their infancy. In this work, we propose a new deep learning configuration with inductive biases that lead agents to generate latent representations of their current goal, yielding a stronger generalization perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09461","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/2110.09461/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":"2110.09461","created_at":"2026-07-05T03:59:41.336825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09461v2","created_at":"2026-07-05T03:59:41.336825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09461","created_at":"2026-07-05T03:59:41.336825+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMUOC4JWJDPJ","created_at":"2026-07-05T03:59:41.336825+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMUOC4JWJDPJJTUE","created_at":"2026-07-05T03:59:41.336825+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMUOC4JW","created_at":"2026-07-05T03:59:41.336825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05932","citing_title":"Skill Expansion and Composition in Parameter Space","ref_index":2006,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI","json":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI.json","graph_json":"https://pith.science/api/pith-number/EMUOC4JWJDPJJTUEQ2BUMRDKNI/graph.json","events_json":"https://pith.science/api/pith-number/EMUOC4JWJDPJJTUEQ2BUMRDKNI/events.json","paper":"https://pith.science/paper/EMUOC4JW"},"agent_actions":{"view_html":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI","download_json":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI.json","view_paper":"https://pith.science/paper/EMUOC4JW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09461&json=true","fetch_graph":"https://pith.science/api/pith-number/EMUOC4JWJDPJJTUEQ2BUMRDKNI/graph.json","fetch_events":"https://pith.science/api/pith-number/EMUOC4JWJDPJJTUEQ2BUMRDKNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI/action/storage_attestation","attest_author":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI/action/author_attestation","sign_citation":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI/action/citation_signature","submit_replication":"https://pith.science/pith/EMUOC4JWJDPJJTUEQ2BUMRDKNI/action/replication_record"}},"created_at":"2026-07-05T03:59:41.336825+00:00","updated_at":"2026-07-05T03:59:41.336825+00:00"}