{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:P53F4JUO65IMR6EZHQJLX4OCJO","short_pith_number":"pith:P53F4JUO","canonical_record":{"source":{"id":"1605.06676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-21T17:20:04Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"7bdd0f055b775a81243852a5726322ecfa92af2c1f326f926be8a0b1261d4b20","abstract_canon_sha256":"cd925d34c4c2d87b4068637b1c71301af5b18d7b1db76cddf0cdc8374ae77f34"},"schema_version":"1.0"},"canonical_sha256":"7f765e268ef750c8f8993c12bbf1c24b8d68d1e0689dd2315a39a4a9e629c773","source":{"kind":"arxiv","id":"1605.06676","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06676","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06676v2","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06676","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"P53F4JUO65IM","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P53F4JUO65IMR6EZ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P53F4JUO","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:P53F4JUO65IMR6EZHQJLX4OCJO","target":"record","payload":{"canonical_record":{"source":{"id":"1605.06676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-21T17:20:04Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"7bdd0f055b775a81243852a5726322ecfa92af2c1f326f926be8a0b1261d4b20","abstract_canon_sha256":"cd925d34c4c2d87b4068637b1c71301af5b18d7b1db76cddf0cdc8374ae77f34"},"schema_version":"1.0"},"canonical_sha256":"7f765e268ef750c8f8993c12bbf1c24b8d68d1e0689dd2315a39a4a9e629c773","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:46.726284Z","signature_b64":"w1QEovxiqKh7GKsc0HcR2SKHQM103UhY2Buvv+McVwNNoapWz3PYfLFfdNt/v2jrOKuqjwTWX5g2IGzjhVdeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f765e268ef750c8f8993c12bbf1c24b8d68d1e0689dd2315a39a4a9e629c773","last_reissued_at":"2026-05-18T01:13:46.725559Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:46.725559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.06676","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":"2026-05-18T01:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0wBFk0VYTo6KDo8LzM5xs3Rulk3XveoTLCXUQnkfZd0uqCd7kzwhFn/KJmButzai6U3trTlkwFYSRiIx0Ld4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:56:40.916134Z"},"content_sha256":"442a66e3c88a3c74c1653645b614e4a3df88eae7298ab9bd4de7c4d858fc1f3b","schema_version":"1.0","event_id":"sha256:442a66e3c88a3c74c1653645b614e4a3df88eae7298ab9bd4de7c4d858fc1f3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:P53F4JUO65IMR6EZHQJLX4OCJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jakob N. Foerster, Nando de Freitas, Shimon Whiteson, Yannis M. Assael","submitted_at":"2016-05-21T17:20:04Z","abstract_excerpt":"We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06676","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":""},"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":"2026-05-18T01:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLGBcuoZdhVA1F7SxmQrjhQW0zjdmbN/p23S6veApKOS09XnHrOptLESB1QSsimhmdVnu2YAPRZocu2TO9+CBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:56:40.916825Z"},"content_sha256":"3cc343bb856ad45841cb74a88e9943e0ed408d0959196337128cf89be807fdc9","schema_version":"1.0","event_id":"sha256:3cc343bb856ad45841cb74a88e9943e0ed408d0959196337128cf89be807fdc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P53F4JUO65IMR6EZHQJLX4OCJO/bundle.json","state_url":"https://pith.science/pith/P53F4JUO65IMR6EZHQJLX4OCJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P53F4JUO65IMR6EZHQJLX4OCJO/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":"2026-05-26T06:56:40Z","links":{"resolver":"https://pith.science/pith/P53F4JUO65IMR6EZHQJLX4OCJO","bundle":"https://pith.science/pith/P53F4JUO65IMR6EZHQJLX4OCJO/bundle.json","state":"https://pith.science/pith/P53F4JUO65IMR6EZHQJLX4OCJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P53F4JUO65IMR6EZHQJLX4OCJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:P53F4JUO65IMR6EZHQJLX4OCJO","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":"cd925d34c4c2d87b4068637b1c71301af5b18d7b1db76cddf0cdc8374ae77f34","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-21T17:20:04Z","title_canon_sha256":"7bdd0f055b775a81243852a5726322ecfa92af2c1f326f926be8a0b1261d4b20"},"schema_version":"1.0","source":{"id":"1605.06676","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06676","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06676v2","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06676","created_at":"2026-05-18T01:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"P53F4JUO65IM","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P53F4JUO65IMR6EZ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P53F4JUO","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:3cc343bb856ad45841cb74a88e9943e0ed408d0959196337128cf89be807fdc9","target":"graph","created_at":"2026-05-18T01:13:46Z","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"},"paper":{"abstract_excerpt":"We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter","authors_text":"Jakob N. Foerster, Nando de Freitas, Shimon Whiteson, Yannis M. Assael","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-21T17:20:04Z","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06676","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":"sha256:442a66e3c88a3c74c1653645b614e4a3df88eae7298ab9bd4de7c4d858fc1f3b","target":"record","created_at":"2026-05-18T01:13:46Z","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":"cd925d34c4c2d87b4068637b1c71301af5b18d7b1db76cddf0cdc8374ae77f34","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-21T17:20:04Z","title_canon_sha256":"7bdd0f055b775a81243852a5726322ecfa92af2c1f326f926be8a0b1261d4b20"},"schema_version":"1.0","source":{"id":"1605.06676","kind":"arxiv","version":2}},"canonical_sha256":"7f765e268ef750c8f8993c12bbf1c24b8d68d1e0689dd2315a39a4a9e629c773","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f765e268ef750c8f8993c12bbf1c24b8d68d1e0689dd2315a39a4a9e629c773","first_computed_at":"2026-05-18T01:13:46.725559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:46.725559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w1QEovxiqKh7GKsc0HcR2SKHQM103UhY2Buvv+McVwNNoapWz3PYfLFfdNt/v2jrOKuqjwTWX5g2IGzjhVdeBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:46.726284Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.06676","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:442a66e3c88a3c74c1653645b614e4a3df88eae7298ab9bd4de7c4d858fc1f3b","sha256:3cc343bb856ad45841cb74a88e9943e0ed408d0959196337128cf89be807fdc9"],"state_sha256":"38911842e34bc212b03558c9c205ab014e7152342369faf7d10b9ce8603908b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jztS77meKAwO+j3KVLrny3kTrWmtLduWDcX138PJM1J2ZyH4wwyXbsa8/pEBPb10JJP0PWITumOv8UijqgLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:56:40.920741Z","bundle_sha256":"c901a092e54e1f79b70288426743c4aaf76ad79db7742a1f3c28aea3e9fc51d6"}}