{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XU7GCZD4LVOCYISK7SQ6JNJZ2O","short_pith_number":"pith:XU7GCZD4","canonical_record":{"source":{"id":"1807.06613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"99bb0046c4b8b13090f177509669bf57946139e69b837ff5ed7ed0ac53716cac","abstract_canon_sha256":"7e61d6d4770697831c2c556737ce60952ad7da4c475f576f6ff5740e9be33928"},"schema_version":"1.0"},"canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","source":{"kind":"arxiv","id":"1807.06613","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06613","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06613v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06613","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"XU7GCZD4LVOC","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XU7GCZD4LVOCYISK","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XU7GCZD4","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XU7GCZD4LVOCYISK7SQ6JNJZ2O","target":"record","payload":{"canonical_record":{"source":{"id":"1807.06613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"99bb0046c4b8b13090f177509669bf57946139e69b837ff5ed7ed0ac53716cac","abstract_canon_sha256":"7e61d6d4770697831c2c556737ce60952ad7da4c475f576f6ff5740e9be33928"},"schema_version":"1.0"},"canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.913373Z","signature_b64":"AqK8H4VDmkllsXnUvf+UYXmLCo4yZEoiThoJ+5/4akL6UzZkRnUyI85vgiuMoBPOZSf9AvkuYlrfvHdBlpaeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","last_reissued_at":"2026-05-17T23:44:02.912863Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.912863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.06613","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePoxqKVwkgSJXp+60DeeZusMPSl6HXiR71kP/MXYWBD1TZqa9DTDMSKwYt3C9M6qgwP7aoQmB9ETd5aZkS9mCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:05:20.661405Z"},"content_sha256":"ad25dd0e052a3d10ace8a68dffa4a425638c997194a17781cfe3c07b552a7301","schema_version":"1.0","event_id":"sha256:ad25dd0e052a3d10ace8a68dffa4a425638c997194a17781cfe3c07b552a7301"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XU7GCZD4LVOCYISK7SQ6JNJZ2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"primary_cat":"cs.MA","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","submitted_at":"2018-07-17T18:27:03Z","abstract_excerpt":"Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06613","kind":"arxiv","version":3},"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":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQk2pMRPajJjKYNrdZipOcYAkSA8UvRZWiPD2e7nirNa+y2uDbLFJx6TAKSPxL/BQw+C0OCL+kI/dSPWIDulAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:05:20.661767Z"},"content_sha256":"37099ffbeb785e4cb86bf1b3090e872850478fae8db9a1bd23c53fba399813cb","schema_version":"1.0","event_id":"sha256:37099ffbeb785e4cb86bf1b3090e872850478fae8db9a1bd23c53fba399813cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/bundle.json","state_url":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/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":"2026-06-11T10:05:20Z","links":{"resolver":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O","bundle":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/bundle.json","state":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XU7GCZD4LVOCYISK7SQ6JNJZ2O","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":"7e61d6d4770697831c2c556737ce60952ad7da4c475f576f6ff5740e9be33928","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","title_canon_sha256":"99bb0046c4b8b13090f177509669bf57946139e69b837ff5ed7ed0ac53716cac"},"schema_version":"1.0","source":{"id":"1807.06613","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06613","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06613v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06613","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"XU7GCZD4LVOC","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XU7GCZD4LVOCYISK","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XU7GCZD4","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:37099ffbeb785e4cb86bf1b3090e872850478fae8db9a1bd23c53fba399813cb","target":"graph","created_at":"2026-05-17T23:44:02Z","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":"Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep mul","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","title":"Deep Reinforcement Learning for Swarm Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06613","kind":"arxiv","version":3},"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:ad25dd0e052a3d10ace8a68dffa4a425638c997194a17781cfe3c07b552a7301","target":"record","created_at":"2026-05-17T23:44:02Z","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":"7e61d6d4770697831c2c556737ce60952ad7da4c475f576f6ff5740e9be33928","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","title_canon_sha256":"99bb0046c4b8b13090f177509669bf57946139e69b837ff5ed7ed0ac53716cac"},"schema_version":"1.0","source":{"id":"1807.06613","kind":"arxiv","version":3}},"canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","first_computed_at":"2026-05-17T23:44:02.912863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:02.912863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqK8H4VDmkllsXnUvf+UYXmLCo4yZEoiThoJ+5/4akL6UzZkRnUyI85vgiuMoBPOZSf9AvkuYlrfvHdBlpaeBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:02.913373Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.06613","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad25dd0e052a3d10ace8a68dffa4a425638c997194a17781cfe3c07b552a7301","sha256:37099ffbeb785e4cb86bf1b3090e872850478fae8db9a1bd23c53fba399813cb"],"state_sha256":"6d7e66b5fa6a33f530ddb60dc2f38136f149536ab490f23190303c2cb69233be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMWDmxgEEqHxc2v+ZrIk46bRCgqAkHVc6OH+1lnRfyGeJ/dI6Qajqu04pTww5kjnGBKqS4alN5Si1QxX6e+iAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:05:20.663796Z","bundle_sha256":"d162d47f8bd0f052c5c328b70ae6bba0ef3972b15a6570ba0d1d26d1f25555e6"}}