{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FFXJIUV2VOU4WLNLP467NT33WB","short_pith_number":"pith:FFXJIUV2","schema_version":"1.0","canonical_sha256":"296e9452baaba9cb2dab7f3df6cf7bb079e01c023ba8904967f43d0fb3d778d2","source":{"kind":"arxiv","id":"1810.04444","version":4},"attestation_state":"computed","paper":{"title":"Learning to Communicate Implicitly By Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haitham Bou Ammar, Ian Davies, Jun Wang, Lisheng Wu, Shihao Zou, Tim Warr, Zheng Tian","submitted_at":"2018-10-10T10:16:55Z","abstract_excerpt":"In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through actions. The first component of this learning process has been well-studied in multi-agent systems, whereas the second --- which is equally crucial for successful collaboration --- has not. To mimic both components mentioned above, thereby completing the learning process, we introduce a novel algorithm: Policy Belief Learning (PBL). PBL uses a belief module to mode"},"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":"1810.04444","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-10T10:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"8ea8fa4706a0b3a599e26eebc49cfe5a56d5860ac8822671a0f8abf12b05df5c","abstract_canon_sha256":"b6b634126d6db4c7b315808500d5b980d93f82e983944d5c477b25f63e4a6aed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:50.858983Z","signature_b64":"5P93NZwqhm11tj9nqL5jHY4FCLGSK/mHEISTgRc3A6OX/NACAFWet/Y5nlcDRVQ3Hqf2djPDuUXTdhpaMYDiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296e9452baaba9cb2dab7f3df6cf7bb079e01c023ba8904967f43d0fb3d778d2","last_reissued_at":"2026-07-05T00:20:50.858525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:50.858525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Communicate Implicitly By Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haitham Bou Ammar, Ian Davies, Jun Wang, Lisheng Wu, Shihao Zou, Tim Warr, Zheng Tian","submitted_at":"2018-10-10T10:16:55Z","abstract_excerpt":"In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through actions. The first component of this learning process has been well-studied in multi-agent systems, whereas the second --- which is equally crucial for successful collaboration --- has not. To mimic both components mentioned above, thereby completing the learning process, we introduce a novel algorithm: Policy Belief Learning (PBL). PBL uses a belief module to mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04444","kind":"arxiv","version":4},"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/1810.04444/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":"1810.04444","created_at":"2026-07-05T00:20:50.858585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04444v4","created_at":"2026-07-05T00:20:50.858585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04444","created_at":"2026-07-05T00:20:50.858585+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFXJIUV2VOU4","created_at":"2026-07-05T00:20:50.858585+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFXJIUV2VOU4WLNL","created_at":"2026-07-05T00:20:50.858585+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFXJIUV2","created_at":"2026-07-05T00:20:50.858585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03335","citing_title":"Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB","json":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB.json","graph_json":"https://pith.science/api/pith-number/FFXJIUV2VOU4WLNLP467NT33WB/graph.json","events_json":"https://pith.science/api/pith-number/FFXJIUV2VOU4WLNLP467NT33WB/events.json","paper":"https://pith.science/paper/FFXJIUV2"},"agent_actions":{"view_html":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB","download_json":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB.json","view_paper":"https://pith.science/paper/FFXJIUV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04444&json=true","fetch_graph":"https://pith.science/api/pith-number/FFXJIUV2VOU4WLNLP467NT33WB/graph.json","fetch_events":"https://pith.science/api/pith-number/FFXJIUV2VOU4WLNLP467NT33WB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB/action/storage_attestation","attest_author":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB/action/author_attestation","sign_citation":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB/action/citation_signature","submit_replication":"https://pith.science/pith/FFXJIUV2VOU4WLNLP467NT33WB/action/replication_record"}},"created_at":"2026-07-05T00:20:50.858585+00:00","updated_at":"2026-07-05T00:20:50.858585+00:00"}