{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4V6PBFUPZYGT75NMEL5IHPLPY4","short_pith_number":"pith:4V6PBFUP","canonical_record":{"source":{"id":"2504.13241","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T17:39:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bab60223d3f223f3d1b130a72540244a1e327bb2549db5a80f61eeea1b313d1","abstract_canon_sha256":"00da21ac1ab0aa193457a04c14a22a9ce72a4dc6ea630d0ab635272d392a96c3"},"schema_version":"1.0"},"canonical_sha256":"e57cf0968fce0d3ff5ac22fa83bd6fc7330e4b70ac5343eb7054bd7fea7ae442","source":{"kind":"arxiv","id":"2504.13241","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13241","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13241v6","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13241","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"4V6PBFUPZYGT","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_16","alias_value":"4V6PBFUPZYGT75NM","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_8","alias_value":"4V6PBFUP","created_at":"2026-07-29T00:24:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4V6PBFUPZYGT75NMEL5IHPLPY4","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13241","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T17:39:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bab60223d3f223f3d1b130a72540244a1e327bb2549db5a80f61eeea1b313d1","abstract_canon_sha256":"00da21ac1ab0aa193457a04c14a22a9ce72a4dc6ea630d0ab635272d392a96c3"},"schema_version":"1.0"},"canonical_sha256":"e57cf0968fce0d3ff5ac22fa83bd6fc7330e4b70ac5343eb7054bd7fea7ae442","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:31.269427Z","signature_b64":"/0E9b4NVEZY3KmhtYJGuxaHGi9KKMWWultpEQJqKVNSHsLp9Pb+CMlX/4fgirHxuCz9EzTHLWt1zHDATkn/ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e57cf0968fce0d3ff5ac22fa83bd6fc7330e4b70ac5343eb7054bd7fea7ae442","last_reissued_at":"2026-07-29T00:24:31.268419Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:31.268419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13241","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hbdhRxwJd1ffifEm8g/C7AA0WR2bdmeiWIdj7A5/C57vcAZaC/4ezgiidEvFRSj/9DRHapki4f7FFUMK+ROUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:53:05.624443Z"},"content_sha256":"a743cb2b684bf1bdc25540a909d60de361ca765f09974140505aabd4fefa887f","schema_version":"1.0","event_id":"sha256:a743cb2b684bf1bdc25540a909d60de361ca765f09974140505aabd4fefa887f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4V6PBFUPZYGT75NMEL5IHPLPY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recursive Deep Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alireza Ramezani, Deniz Erdogmus, Michael Potter, Owen Howell, Pau Closas, Paul Ghanem, Tales Imbiriba","submitted_at":"2025-04-17T17:39:35Z","abstract_excerpt":"Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy games. Deep Inverse Reinforcement Learning (IRL) methods based on maximum entropy principles show promise in recovering adversaries goals but are typically offline, require large batch sizes with gradient descent, and rely on first-order updates, limiting their applicability in real-time scenarios. We propose an online Recursive Deep Inverse Reinforcement Learning (RDIRL) approach to recover the cost function governi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13241","kind":"arxiv","version":6},"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/2504.13241/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":"2026-07-29T00:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0UYNyFa9DWJJtiHV6tCZ8QUpMuusUtrXjx9s2II0oGQjglqVECwUizi4S5uzs0DiOKcaxy7iVLqMVT5SgkJeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:53:05.624950Z"},"content_sha256":"ab3bf5372f84dab68cae0c78076dabb23eebbcc7919daad1e297ddcbe28d4eb8","schema_version":"1.0","event_id":"sha256:ab3bf5372f84dab68cae0c78076dabb23eebbcc7919daad1e297ddcbe28d4eb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/bundle.json","state_url":"https://pith.science/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/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":"2026-08-11T01:53:05Z","links":{"resolver":"https://pith.science/pith/4V6PBFUPZYGT75NMEL5IHPLPY4","bundle":"https://pith.science/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/bundle.json","state":"https://pith.science/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4V6PBFUPZYGT75NMEL5IHPLPY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4V6PBFUPZYGT75NMEL5IHPLPY4","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":"00da21ac1ab0aa193457a04c14a22a9ce72a4dc6ea630d0ab635272d392a96c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T17:39:35Z","title_canon_sha256":"0bab60223d3f223f3d1b130a72540244a1e327bb2549db5a80f61eeea1b313d1"},"schema_version":"1.0","source":{"id":"2504.13241","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13241","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13241v6","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13241","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"4V6PBFUPZYGT","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_16","alias_value":"4V6PBFUPZYGT75NM","created_at":"2026-07-29T00:24:31Z"},{"alias_kind":"pith_short_8","alias_value":"4V6PBFUP","created_at":"2026-07-29T00:24:31Z"}],"graph_snapshots":[{"event_id":"sha256:ab3bf5372f84dab68cae0c78076dabb23eebbcc7919daad1e297ddcbe28d4eb8","target":"graph","created_at":"2026-07-29T00:24:31Z","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/2504.13241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy games. Deep Inverse Reinforcement Learning (IRL) methods based on maximum entropy principles show promise in recovering adversaries goals but are typically offline, require large batch sizes with gradient descent, and rely on first-order updates, limiting their applicability in real-time scenarios. We propose an online Recursive Deep Inverse Reinforcement Learning (RDIRL) approach to recover the cost function governi","authors_text":"Alireza Ramezani, Deniz Erdogmus, Michael Potter, Owen Howell, Pau Closas, Paul Ghanem, Tales Imbiriba","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T17:39:35Z","title":"Recursive Deep Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13241","kind":"arxiv","version":6},"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:a743cb2b684bf1bdc25540a909d60de361ca765f09974140505aabd4fefa887f","target":"record","created_at":"2026-07-29T00:24:31Z","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":"00da21ac1ab0aa193457a04c14a22a9ce72a4dc6ea630d0ab635272d392a96c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T17:39:35Z","title_canon_sha256":"0bab60223d3f223f3d1b130a72540244a1e327bb2549db5a80f61eeea1b313d1"},"schema_version":"1.0","source":{"id":"2504.13241","kind":"arxiv","version":6}},"canonical_sha256":"e57cf0968fce0d3ff5ac22fa83bd6fc7330e4b70ac5343eb7054bd7fea7ae442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e57cf0968fce0d3ff5ac22fa83bd6fc7330e4b70ac5343eb7054bd7fea7ae442","first_computed_at":"2026-07-29T00:24:31.268419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:31.268419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0E9b4NVEZY3KmhtYJGuxaHGi9KKMWWultpEQJqKVNSHsLp9Pb+CMlX/4fgirHxuCz9EzTHLWt1zHDATkn/ZCw==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:31.269427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13241","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a743cb2b684bf1bdc25540a909d60de361ca765f09974140505aabd4fefa887f","sha256:ab3bf5372f84dab68cae0c78076dabb23eebbcc7919daad1e297ddcbe28d4eb8"],"state_sha256":"f55438319c6450acdbe198afcc39ab3122cb26112c5bc0431aeefaa4eff3131b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggiZYPr2Jl0SZF05kVJcIJcpqH7MhLvXkhdPU5pNahcgiSrTWMk2Ase8atBFaErGLoZabLccn45fU2ShlW8kAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:53:05.630911Z","bundle_sha256":"ce8aba648db438f8232b43af1eb217188d4be32cebd626af391807e20a0de66e"}}