{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:LGEZWJKDD3H2JUHCVCBGQDJYYU","short_pith_number":"pith:LGEZWJKD","canonical_record":{"source":{"id":"1602.05450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"title_canon_sha256":"f6b58f60f80203b00093bdb878dba45a1c1a037fd0cf56a762c3be9a13964582","abstract_canon_sha256":"9a0b7787634c8c7ff7177d5a8c29e0bf659eafdf82ae542095b1dcfa775dbb85"},"schema_version":"1.0"},"canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","source":{"kind":"arxiv","id":"1602.05450","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.05450","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"1602.05450v2","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05450","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"LGEZWJKDD3H2","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LGEZWJKDD3H2JUHC","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LGEZWJKD","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:LGEZWJKDD3H2JUHCVCBGQDJYYU","target":"record","payload":{"canonical_record":{"source":{"id":"1602.05450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"title_canon_sha256":"f6b58f60f80203b00093bdb878dba45a1c1a037fd0cf56a762c3be9a13964582","abstract_canon_sha256":"9a0b7787634c8c7ff7177d5a8c29e0bf659eafdf82ae542095b1dcfa775dbb85"},"schema_version":"1.0"},"canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:01.332652Z","signature_b64":"3obe0xIGmQRaUSkY5IU8Sw7U0CygmAaMRgmYnI6UQhV+eszTGCGLwS5xIULqPemnZ2nUaHVd2rwcAB8QxR49Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","last_reissued_at":"2026-05-18T00:48:01.332033Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:01.332033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.05450","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":"2026-05-18T00:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLmmWoZwXPwcA5mk6u6SjJ9+aYOA6UaHLz2CfW9xsgsnUaTVc1O5LKmoAXKXkiAjfLOsCfWKklgwQjneHUVzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:03:39.431273Z"},"content_sha256":"97fdc611f8a04ba07503066e91be298e494ba73f88c99e118c0dd5f2f4f6b601","schema_version":"1.0","event_id":"sha256:97fdc611f8a04ba07503066e91be298e494ba73f88c99e118c0dd5f2f4f6b601"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:LGEZWJKDD3H2JUHCVCBGQDJYYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning in Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY"],"primary_cat":"stat.ML","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Heinz Koeppl, Wasiur R. KhudaBukhsh","submitted_at":"2016-02-17T15:19:56Z","abstract_excerpt":"Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems. In particular, we make the following contributions to the field: 1) We introduce the swarMDP framework, a sub-class of decentralized partially observable Markov decision processes endowed with a swarm characterization. 2) Exploiting the inherent homoge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05450","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":"2026-05-18T00:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y5q1hfJsGl3hz5CZPzLD+Gmhap0f5hOS7nSSGLSOneSrchXp5nn7z905s5FTpCyLWTLExOUI/aLtEY3OVdAZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:03:39.431637Z"},"content_sha256":"2cdeb35dd74063d0a9a74cc4af2e9b58e5736d437384264517d238f65b041a7a","schema_version":"1.0","event_id":"sha256:2cdeb35dd74063d0a9a74cc4af2e9b58e5736d437384264517d238f65b041a7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/bundle.json","state_url":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/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":"2026-06-11T12:03:39Z","links":{"resolver":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU","bundle":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/bundle.json","state":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LGEZWJKDD3H2JUHCVCBGQDJYYU","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":"9a0b7787634c8c7ff7177d5a8c29e0bf659eafdf82ae542095b1dcfa775dbb85","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","title_canon_sha256":"f6b58f60f80203b00093bdb878dba45a1c1a037fd0cf56a762c3be9a13964582"},"schema_version":"1.0","source":{"id":"1602.05450","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.05450","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"1602.05450v2","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05450","created_at":"2026-05-18T00:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"LGEZWJKDD3H2","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LGEZWJKDD3H2JUHC","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LGEZWJKD","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:2cdeb35dd74063d0a9a74cc4af2e9b58e5736d437384264517d238f65b041a7a","target":"graph","created_at":"2026-05-18T00:48:01Z","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":"Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems. In particular, we make the following contributions to the field: 1) We introduce the swarMDP framework, a sub-class of decentralized partially observable Markov decision processes endowed with a swarm characterization. 2) Exploiting the inherent homoge","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Heinz Koeppl, Wasiur R. KhudaBukhsh","cross_cats":["cs.AI","cs.MA","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","title":"Inverse Reinforcement Learning in Swarm Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05450","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":"sha256:97fdc611f8a04ba07503066e91be298e494ba73f88c99e118c0dd5f2f4f6b601","target":"record","created_at":"2026-05-18T00:48:01Z","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":"9a0b7787634c8c7ff7177d5a8c29e0bf659eafdf82ae542095b1dcfa775dbb85","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","title_canon_sha256":"f6b58f60f80203b00093bdb878dba45a1c1a037fd0cf56a762c3be9a13964582"},"schema_version":"1.0","source":{"id":"1602.05450","kind":"arxiv","version":2}},"canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","first_computed_at":"2026-05-18T00:48:01.332033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:01.332033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3obe0xIGmQRaUSkY5IU8Sw7U0CygmAaMRgmYnI6UQhV+eszTGCGLwS5xIULqPemnZ2nUaHVd2rwcAB8QxR49Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:01.332652Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.05450","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97fdc611f8a04ba07503066e91be298e494ba73f88c99e118c0dd5f2f4f6b601","sha256:2cdeb35dd74063d0a9a74cc4af2e9b58e5736d437384264517d238f65b041a7a"],"state_sha256":"82d993ea94e5d9235692f4e0fcc52af299edc1366f5b1c4af7accaf4e5075d6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2y41/zMIsw7WUDCqbM6GC98XCot0uOdZ/WIU+L5BlrkyflPdFqVhSSDKmNs4rknu7KaDY4um3t48EdW7Ryd7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:03:39.433564Z","bundle_sha256":"29f1ee0a59764e41946ff89564e06cf6da14dd46be576c213b3b1633e9ee4fec"}}