{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C7ULMUVUUFQTEHJ35V7SVHHRZV","short_pith_number":"pith:C7ULMUVU","canonical_record":{"source":{"id":"2512.08052","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T21:21:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eaeb06e35b1b7cad93ff2437b3c2fcdf6389a5de7cf206eec4e18c586831c29a","abstract_canon_sha256":"56dc0b8ce238d6e43a5441600fd3dab81dc559af35fd7a8a2b9eed1776b3a2c5"},"schema_version":"1.0"},"canonical_sha256":"17e8b652b4a161321d3bed7f2a9cf1cd69e4595de3150ed5fc0fb59574659c90","source":{"kind":"arxiv","id":"2512.08052","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.08052","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2512.08052v3","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.08052","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"C7ULMUVUUFQT","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"C7ULMUVUUFQTEHJ3","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"C7ULMUVU","created_at":"2026-05-20T00:01:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C7ULMUVUUFQTEHJ35V7SVHHRZV","target":"record","payload":{"canonical_record":{"source":{"id":"2512.08052","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T21:21:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eaeb06e35b1b7cad93ff2437b3c2fcdf6389a5de7cf206eec4e18c586831c29a","abstract_canon_sha256":"56dc0b8ce238d6e43a5441600fd3dab81dc559af35fd7a8a2b9eed1776b3a2c5"},"schema_version":"1.0"},"canonical_sha256":"17e8b652b4a161321d3bed7f2a9cf1cd69e4595de3150ed5fc0fb59574659c90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:37.603830Z","signature_b64":"+wcbwR1vEIfTV0m2BVaxRuA0ntI20NHQmSpncRSHtqjnxEXwKdTztE3+Qfk8Y18kFuYstvnpBT5aXKGSDar3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e8b652b4a161321d3bed7f2a9cf1cd69e4595de3150ed5fc0fb59574659c90","last_reissued_at":"2026-05-20T00:01:37.602938Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:37.602938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.08052","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":"2026-05-20T00:01:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yq3fWa73VASIwUpGCfMOoqDtL7LEEHlynJNjMEecQWexW7WbEwD9597awxUpF0DrMcsGQXIs+IwCjXNdtvVHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T03:28:29.083532Z"},"content_sha256":"8d3ef0932d3ae637db43397ed027b985ac103e68afb4738eb5abc53a0e9564f0","schema_version":"1.0","event_id":"sha256:8d3ef0932d3ae637db43397ed027b985ac103e68afb4738eb5abc53a0e9564f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C7ULMUVUUFQTEHJ35V7SVHHRZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Introduction to Deep Reinforcement and Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Pedro Santana","submitted_at":"2025-12-08T21:21:01Z","abstract_excerpt":"Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.08052","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.08052/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":"2026-05-20T00:01:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqmB80/T5s3lq2lCH7xRbKwwQr5iOTr1SdWWmQ6lKMrm3/QLo9pGjigDt+COJBxGkJUaZhccvvv/Vr/weCZoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T03:28:29.083913Z"},"content_sha256":"730c62523128d811570bc49f7ffb981ca8feb4939669e593fa69ae73a8ba7568","schema_version":"1.0","event_id":"sha256:730c62523128d811570bc49f7ffb981ca8feb4939669e593fa69ae73a8ba7568"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/bundle.json","state_url":"https://pith.science/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/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":"2026-06-26T03:28:29Z","links":{"resolver":"https://pith.science/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV","bundle":"https://pith.science/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/bundle.json","state":"https://pith.science/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7ULMUVUUFQTEHJ35V7SVHHRZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C7ULMUVUUFQTEHJ35V7SVHHRZV","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":"56dc0b8ce238d6e43a5441600fd3dab81dc559af35fd7a8a2b9eed1776b3a2c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T21:21:01Z","title_canon_sha256":"eaeb06e35b1b7cad93ff2437b3c2fcdf6389a5de7cf206eec4e18c586831c29a"},"schema_version":"1.0","source":{"id":"2512.08052","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.08052","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2512.08052v3","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.08052","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"C7ULMUVUUFQT","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"C7ULMUVUUFQTEHJ3","created_at":"2026-05-20T00:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"C7ULMUVU","created_at":"2026-05-20T00:01:37Z"}],"graph_snapshots":[{"event_id":"sha256:730c62523128d811570bc49f7ffb981ca8feb4939669e593fa69ae73a8ba7568","target":"graph","created_at":"2026-05-20T00:01:37Z","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/2512.08052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach","authors_text":"Pedro Santana","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T21:21:01Z","title":"An Introduction to Deep Reinforcement and Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.08052","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":"sha256:8d3ef0932d3ae637db43397ed027b985ac103e68afb4738eb5abc53a0e9564f0","target":"record","created_at":"2026-05-20T00:01:37Z","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":"56dc0b8ce238d6e43a5441600fd3dab81dc559af35fd7a8a2b9eed1776b3a2c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T21:21:01Z","title_canon_sha256":"eaeb06e35b1b7cad93ff2437b3c2fcdf6389a5de7cf206eec4e18c586831c29a"},"schema_version":"1.0","source":{"id":"2512.08052","kind":"arxiv","version":3}},"canonical_sha256":"17e8b652b4a161321d3bed7f2a9cf1cd69e4595de3150ed5fc0fb59574659c90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17e8b652b4a161321d3bed7f2a9cf1cd69e4595de3150ed5fc0fb59574659c90","first_computed_at":"2026-05-20T00:01:37.602938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:37.602938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wcbwR1vEIfTV0m2BVaxRuA0ntI20NHQmSpncRSHtqjnxEXwKdTztE3+Qfk8Y18kFuYstvnpBT5aXKGSDar3CQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:37.603830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.08052","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d3ef0932d3ae637db43397ed027b985ac103e68afb4738eb5abc53a0e9564f0","sha256:730c62523128d811570bc49f7ffb981ca8feb4939669e593fa69ae73a8ba7568"],"state_sha256":"c0a2bc1d7cf8120c587d38b0792fda4eb412ad7f4fc8e343dd52d34b0ee83ef1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ni2boMpsyN5GM9QVGuBerWH8574zBi++yfHxHb24thAoKeF+7dU72eIV3LxEJ33sK6RsmD1fDNdp0nIa3AwzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T03:28:29.086064Z","bundle_sha256":"d172172e317b08876a14f0f7450a4dbe87adbf8f3f783df1baf07fd857916581"}}