{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCXUZN57Z7ECUMMZWXK7OUZ3QG","short_pith_number":"pith:MCXUZN57","schema_version":"1.0","canonical_sha256":"60af4cb7bfcfc82a3199b5d5f7533b81ab122e1df5527a5479a3fa4061bcc9fa","source":{"kind":"arxiv","id":"2410.22194","version":1},"attestation_state":"computed","paper":{"title":"ADAM: An Embodied Causal Agent in Open-World Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Chaochao Lu, Shu Yu","submitted_at":"2024-10-29T16:32:01Z","abstract_excerpt":"In open-world environments like Minecraft, existing agents face challenges in continuously learning structured knowledge, particularly causality. These challenges stem from the opacity inherent in black-box models and an excessive reliance on prior knowledge during training, which impair their interpretability and generalization capability. To this end, we introduce ADAM, An emboDied causal Agent in Minecraft, that can autonomously navigate the open world, perceive multimodal contexts, learn causal world knowledge, and tackle complex tasks through lifelong learning. ADAM is empowered by four k"},"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":"2410.22194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-29T16:32:01Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ba2181b402b2995a86e824d9850ed906c2b772816cb5adc0690569c2d815b5e1","abstract_canon_sha256":"ab76826083b5aadc1eddd3ee89803b8af48ef16589da1c4bad1799a567f552cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:05.361940Z","signature_b64":"56MoOsWYdSO5a8qjoLkdYnqsNdN6mHcJueJeigQ0Wzxv1069Om76KBN4qqKBddRPgZ+TPnREKwbHWb7981V3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60af4cb7bfcfc82a3199b5d5f7533b81ab122e1df5527a5479a3fa4061bcc9fa","last_reissued_at":"2026-07-05T09:28:05.361461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:05.361461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADAM: An Embodied Causal Agent in Open-World Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Chaochao Lu, Shu Yu","submitted_at":"2024-10-29T16:32:01Z","abstract_excerpt":"In open-world environments like Minecraft, existing agents face challenges in continuously learning structured knowledge, particularly causality. These challenges stem from the opacity inherent in black-box models and an excessive reliance on prior knowledge during training, which impair their interpretability and generalization capability. To this end, we introduce ADAM, An emboDied causal Agent in Minecraft, that can autonomously navigate the open world, perceive multimodal contexts, learn causal world knowledge, and tackle complex tasks through lifelong learning. ADAM is empowered by four k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22194","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/2410.22194/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":"2410.22194","created_at":"2026-07-05T09:28:05.361523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22194v1","created_at":"2026-07-05T09:28:05.361523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22194","created_at":"2026-07-05T09:28:05.361523+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCXUZN57Z7EC","created_at":"2026-07-05T09:28:05.361523+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCXUZN57Z7ECUMMZ","created_at":"2026-07-05T09:28:05.361523+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCXUZN57","created_at":"2026-07-05T09:28:05.361523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18975","citing_title":"Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08340","citing_title":"Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG","json":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG.json","graph_json":"https://pith.science/api/pith-number/MCXUZN57Z7ECUMMZWXK7OUZ3QG/graph.json","events_json":"https://pith.science/api/pith-number/MCXUZN57Z7ECUMMZWXK7OUZ3QG/events.json","paper":"https://pith.science/paper/MCXUZN57"},"agent_actions":{"view_html":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG","download_json":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG.json","view_paper":"https://pith.science/paper/MCXUZN57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22194&json=true","fetch_graph":"https://pith.science/api/pith-number/MCXUZN57Z7ECUMMZWXK7OUZ3QG/graph.json","fetch_events":"https://pith.science/api/pith-number/MCXUZN57Z7ECUMMZWXK7OUZ3QG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG/action/storage_attestation","attest_author":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG/action/author_attestation","sign_citation":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG/action/citation_signature","submit_replication":"https://pith.science/pith/MCXUZN57Z7ECUMMZWXK7OUZ3QG/action/replication_record"}},"created_at":"2026-07-05T09:28:05.361523+00:00","updated_at":"2026-07-05T09:28:05.361523+00:00"}