{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:XVBIJG6RCIEHDZFKBVPQOTBYP2","short_pith_number":"pith:XVBIJG6R","canonical_record":{"source":{"id":"1301.5488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3acc572b3a046fb3820f6c9f8406bb895d0bd07a0dfdaa4a3d2218e902ada20a","abstract_canon_sha256":"b6dc6ba63e6fa36c1d013f55c942c32a8d450017bc82b080e2a81affdc9ff20d"},"schema_version":"1.0"},"canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","source":{"kind":"arxiv","id":"1301.5488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.5488","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"1301.5488v1","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.5488","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"XVBIJG6RCIEH","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"XVBIJG6RCIEHDZFK","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"XVBIJG6R","created_at":"2026-05-18T12:28:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:XVBIJG6RCIEHDZFKBVPQOTBYP2","target":"record","payload":{"canonical_record":{"source":{"id":"1301.5488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3acc572b3a046fb3820f6c9f8406bb895d0bd07a0dfdaa4a3d2218e902ada20a","abstract_canon_sha256":"b6dc6ba63e6fa36c1d013f55c942c32a8d450017bc82b080e2a81affdc9ff20d"},"schema_version":"1.0"},"canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:39.649479Z","signature_b64":"V3yIw1AX5ObpNEnB59tgJ7kGeaR6gtfQ/X+y8uqyCXsehGsH3OlJPVRXa6YG9GUeUC1oR67MqaPhsfSLiqdsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","last_reissued_at":"2026-05-18T03:35:39.648713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:39.648713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.5488","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8P27Lox6XZpScy6QBcbs7q6tw6lGGV2KK61TBLfMaueHTmKLU3SKAvvvEhpn3nixpGEP8UohPhy7mxTGaraBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:34.989123Z"},"content_sha256":"9efdd766eade4b6dd86f816017f8d82dc67612acf9d184cae20654b76d9d9430","schema_version":"1.0","event_id":"sha256:9efdd766eade4b6dd86f816017f8d82dc67612acf9d184cae20654b76d9d9430"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:XVBIJG6RCIEHDZFKBVPQOTBYP2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Francisco Melo, Manuel Lopes","submitted_at":"2013-01-23T12:54:09Z","abstract_excerpt":"This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning algorithm that enables the learning agent to query the expert for more informative demonstrations, thus leading to more sample-efficient learning. For this novel algorithm (Generalized Binary Search for Inverse Reinforcement Learning, or GBS-IRL), we provide a theoretical bound on sample complexity and illustrate its applicability on several different tasks. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.5488","kind":"arxiv","version":1},"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":"2026-05-18T03:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7p2zhZiFbgi7qF8wEqCbkHyjXBdi9zEORULqoEgfsw5D4Lty6T2TcKrOoW0ZR1UzooUfiAcVvtCJBJk/0DtEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:34.989852Z"},"content_sha256":"2277bcd9d55d72958b61ea88c52304001840c8c56c2e20818ec4b12fe4fca85a","schema_version":"1.0","event_id":"sha256:2277bcd9d55d72958b61ea88c52304001840c8c56c2e20818ec4b12fe4fca85a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/bundle.json","state_url":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/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":"2026-05-27T15:56:34Z","links":{"resolver":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2","bundle":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/bundle.json","state":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:XVBIJG6RCIEHDZFKBVPQOTBYP2","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":"b6dc6ba63e6fa36c1d013f55c942c32a8d450017bc82b080e2a81affdc9ff20d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","title_canon_sha256":"3acc572b3a046fb3820f6c9f8406bb895d0bd07a0dfdaa4a3d2218e902ada20a"},"schema_version":"1.0","source":{"id":"1301.5488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.5488","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"1301.5488v1","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.5488","created_at":"2026-05-18T03:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"XVBIJG6RCIEH","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"XVBIJG6RCIEHDZFK","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"XVBIJG6R","created_at":"2026-05-18T12:28:06Z"}],"graph_snapshots":[{"event_id":"sha256:2277bcd9d55d72958b61ea88c52304001840c8c56c2e20818ec4b12fe4fca85a","target":"graph","created_at":"2026-05-18T03:35:39Z","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":"This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning algorithm that enables the learning agent to query the expert for more informative demonstrations, thus leading to more sample-efficient learning. For this novel algorithm (Generalized Binary Search for Inverse Reinforcement Learning, or GBS-IRL), we provide a theoretical bound on sample complexity and illustrate its applicability on several different tasks. To ","authors_text":"Francisco Melo, Manuel Lopes","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","title":"Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.5488","kind":"arxiv","version":1},"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":"sha256:9efdd766eade4b6dd86f816017f8d82dc67612acf9d184cae20654b76d9d9430","target":"record","created_at":"2026-05-18T03:35:39Z","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":"b6dc6ba63e6fa36c1d013f55c942c32a8d450017bc82b080e2a81affdc9ff20d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","title_canon_sha256":"3acc572b3a046fb3820f6c9f8406bb895d0bd07a0dfdaa4a3d2218e902ada20a"},"schema_version":"1.0","source":{"id":"1301.5488","kind":"arxiv","version":1}},"canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","first_computed_at":"2026-05-18T03:35:39.648713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:35:39.648713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3yIw1AX5ObpNEnB59tgJ7kGeaR6gtfQ/X+y8uqyCXsehGsH3OlJPVRXa6YG9GUeUC1oR67MqaPhsfSLiqdsAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:35:39.649479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.5488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9efdd766eade4b6dd86f816017f8d82dc67612acf9d184cae20654b76d9d9430","sha256:2277bcd9d55d72958b61ea88c52304001840c8c56c2e20818ec4b12fe4fca85a"],"state_sha256":"b082147c1a03b17b0dd975ab880967962ef9ded170cdfa4124bf498117d35980"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjUk3jAhuNojPfdhjsBfyjfQ0wSqzEQZfiQhGcz4o4uXcR1qDCQpWJbdlESfGknwK7cuDXjgMSPUsjQt8OtGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:56:34.993720Z","bundle_sha256":"4f7552a6f1f1d268be14a4bee4c36a2dfab48a0262f5fbe8daad73635f55c9e5"}}