{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XOCJZKWWC4QRBUURYDEYSAVP2N","short_pith_number":"pith:XOCJZKWW","canonical_record":{"source":{"id":"2107.09356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T09:19:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"763ae33243e6c0c58934172b2248e95738ca7f128d1632e8ff19ccbcb4ed134d","abstract_canon_sha256":"7ab7c4e1e00ec1d39ac51e33fc5e501d299f1a19dcc676c877154e64494ca381"},"schema_version":"1.0"},"canonical_sha256":"bb849caad6172110d291c0c98902afd36cc25792dfe35b96dcd7c2a73fd8c209","source":{"kind":"arxiv","id":"2107.09356","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09356","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09356v2","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09356","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"XOCJZKWWC4QR","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"XOCJZKWWC4QRBUUR","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"XOCJZKWW","created_at":"2026-07-05T02:59:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XOCJZKWWC4QRBUURYDEYSAVP2N","target":"record","payload":{"canonical_record":{"source":{"id":"2107.09356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T09:19:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"763ae33243e6c0c58934172b2248e95738ca7f128d1632e8ff19ccbcb4ed134d","abstract_canon_sha256":"7ab7c4e1e00ec1d39ac51e33fc5e501d299f1a19dcc676c877154e64494ca381"},"schema_version":"1.0"},"canonical_sha256":"bb849caad6172110d291c0c98902afd36cc25792dfe35b96dcd7c2a73fd8c209","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:38.384955Z","signature_b64":"02WK0agCUh4lS6izRdd+K8woGSa0ODqBYQKwuJMUBllbedYWxt9Qm9J7BJHQvCPQDhuJIZYhfzWgPq+gMQGmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb849caad6172110d291c0c98902afd36cc25792dfe35b96dcd7c2a73fd8c209","last_reissued_at":"2026-07-05T02:59:38.384467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:38.384467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.09356","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":"2026-07-05T02:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jup1tI97tZlS+ylSDce1GblxQvYUFhaxyE7GHqPxWXX3MePbOBloXXCoOcPlor2nB4R1SOb5LRfaoIpFsqkkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:08.245798Z"},"content_sha256":"14ce4a6b546b07314ff38fe5b7d54c17fb25ff0aaf34cc6ead645f88c5f2067c","schema_version":"1.0","event_id":"sha256:14ce4a6b546b07314ff38fe5b7d54c17fb25ff0aaf34cc6ead645f88c5f2067c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XOCJZKWWC4QRBUURYDEYSAVP2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Collaborative Reinforcement Learning Agents that Communicate Through Text-Based Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Herman A. Engelbrecht, Kevin Eloff","submitted_at":"2021-07-20T09:19:29Z","abstract_excerpt":"Communication between agents in collaborative multi-agent settings is in general implicit or a direct data stream. This paper considers text-based natural language as a novel form of communication between multiple agents trained with reinforcement learning. This could be considered first steps toward a truly autonomous communication without the need to define a limited set of instructions, and natural collaboration between humans and robots. Inspired by the game of Blind Leads, we propose an environment where one agent uses natural language instructions to guide another through a maze. We test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09356","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/2107.09356/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":"2026-07-05T02:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Az/6SO8qbSELPcMNjo06uQKZFYx8m4Lj0CbrVPRC5aaUsa4eKfEyFl8OzeTxwzl81sLPeaXu6Bcl43FGmv4vAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:08.246159Z"},"content_sha256":"d79f08e01bb2b2d65dd4d8db888cc5d3e98dd476e52c39ad4a0f1cca9e8f8981","schema_version":"1.0","event_id":"sha256:d79f08e01bb2b2d65dd4d8db888cc5d3e98dd476e52c39ad4a0f1cca9e8f8981"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/bundle.json","state_url":"https://pith.science/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/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":"2026-07-07T12:43:08Z","links":{"resolver":"https://pith.science/pith/XOCJZKWWC4QRBUURYDEYSAVP2N","bundle":"https://pith.science/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/bundle.json","state":"https://pith.science/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOCJZKWWC4QRBUURYDEYSAVP2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XOCJZKWWC4QRBUURYDEYSAVP2N","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":"7ab7c4e1e00ec1d39ac51e33fc5e501d299f1a19dcc676c877154e64494ca381","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T09:19:29Z","title_canon_sha256":"763ae33243e6c0c58934172b2248e95738ca7f128d1632e8ff19ccbcb4ed134d"},"schema_version":"1.0","source":{"id":"2107.09356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09356","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09356v2","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09356","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"XOCJZKWWC4QR","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"XOCJZKWWC4QRBUUR","created_at":"2026-07-05T02:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"XOCJZKWW","created_at":"2026-07-05T02:59:38Z"}],"graph_snapshots":[{"event_id":"sha256:d79f08e01bb2b2d65dd4d8db888cc5d3e98dd476e52c39ad4a0f1cca9e8f8981","target":"graph","created_at":"2026-07-05T02:59:38Z","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/2107.09356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Communication between agents in collaborative multi-agent settings is in general implicit or a direct data stream. This paper considers text-based natural language as a novel form of communication between multiple agents trained with reinforcement learning. This could be considered first steps toward a truly autonomous communication without the need to define a limited set of instructions, and natural collaboration between humans and robots. Inspired by the game of Blind Leads, we propose an environment where one agent uses natural language instructions to guide another through a maze. We test","authors_text":"Herman A. Engelbrecht, Kevin Eloff","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T09:19:29Z","title":"Toward Collaborative Reinforcement Learning Agents that Communicate Through Text-Based Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09356","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":"sha256:14ce4a6b546b07314ff38fe5b7d54c17fb25ff0aaf34cc6ead645f88c5f2067c","target":"record","created_at":"2026-07-05T02:59:38Z","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":"7ab7c4e1e00ec1d39ac51e33fc5e501d299f1a19dcc676c877154e64494ca381","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T09:19:29Z","title_canon_sha256":"763ae33243e6c0c58934172b2248e95738ca7f128d1632e8ff19ccbcb4ed134d"},"schema_version":"1.0","source":{"id":"2107.09356","kind":"arxiv","version":2}},"canonical_sha256":"bb849caad6172110d291c0c98902afd36cc25792dfe35b96dcd7c2a73fd8c209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb849caad6172110d291c0c98902afd36cc25792dfe35b96dcd7c2a73fd8c209","first_computed_at":"2026-07-05T02:59:38.384467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:38.384467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"02WK0agCUh4lS6izRdd+K8woGSa0ODqBYQKwuJMUBllbedYWxt9Qm9J7BJHQvCPQDhuJIZYhfzWgPq+gMQGmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:38.384955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14ce4a6b546b07314ff38fe5b7d54c17fb25ff0aaf34cc6ead645f88c5f2067c","sha256:d79f08e01bb2b2d65dd4d8db888cc5d3e98dd476e52c39ad4a0f1cca9e8f8981"],"state_sha256":"ddff0a0d6da51e8a1aef08945754de20f0b1505369299e5364903df6fc57d841"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ph49cl87/Pa22kvB51wIB6tXYT9CJTE6CkskC7ffmRxjjNFU+u7vAWDYwYMg8+MUxNTjDsDz1CTLXL4nnOYCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:43:08.248048Z","bundle_sha256":"ff6d6fddc008d50cf73257d3c3a4463d4d7f47c611816702520441f6ccdaec87"}}