{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5A4EZ44FRM4ASYMSZ3RHX2LT7A","short_pith_number":"pith:5A4EZ44F","canonical_record":{"source":{"id":"1905.11867","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15696678b98ae01eaf8116a712a260aa15b405b541ccf285290a8191f0a38f1f","abstract_canon_sha256":"a10ea9a5767a42a60a984901e5a9a12d4ada424246a4c0eb34454a15778f0d29"},"schema_version":"1.0"},"canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","source":{"kind":"arxiv","id":"1905.11867","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11867","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11867v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11867","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"5A4EZ44FRM4A","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5A4EZ44FRM4ASYMS","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5A4EZ44F","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5A4EZ44FRM4ASYMSZ3RHX2LT7A","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11867","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15696678b98ae01eaf8116a712a260aa15b405b541ccf285290a8191f0a38f1f","abstract_canon_sha256":"a10ea9a5767a42a60a984901e5a9a12d4ada424246a4c0eb34454a15778f0d29"},"schema_version":"1.0"},"canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.082638Z","signature_b64":"B2B5qwU4mvOT3yBsZyYP1Knqg3K5RssfA9sPCWSh3AYqRVZ8yg5iF2Jo/ngDjYS+2wioD8PM4sMQlIBF+JS6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","last_reissued_at":"2026-05-17T23:44:02.082131Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.082131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11867","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":"15HtSjqfCAscELzet//ColEXeN3thhv29eD1KKTNA8T4NV29yTO9Y4cuP60Ueogv6NMy4iuKuiBu5EIm6gb7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:39:23.320534Z"},"content_sha256":"f6ad7c0acc75bf8dc733478197b51434a7191cc58df1d83c9b4ba8fbef932db4","schema_version":"1.0","event_id":"sha256:f6ad7c0acc75bf8dc733478197b51434a7191cc58df1d83c9b4ba8fbef932db4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5A4EZ44FRM4ASYMSZ3RHX2LT7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interactive Teaching Algorithms for 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":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher","submitted_at":"2019-05-28T15:03:14Z","abstract_excerpt":"We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11867","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":"/5FLONtxqXgQ6jhBakQpEDFXTdCUEq9wwaOedy1oFtNVedgu1+UaazDd3/K+mIjZyDMsaPLmt09+ZGSKj6YEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:39:23.321232Z"},"content_sha256":"d7597146a8dffd2edf512a91a690b4d00a711689c3efec7b0f7b928ba3346992","schema_version":"1.0","event_id":"sha256:d7597146a8dffd2edf512a91a690b4d00a711689c3efec7b0f7b928ba3346992"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/bundle.json","state_url":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/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":"2026-06-11T00:39:23Z","links":{"resolver":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A","bundle":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/bundle.json","state":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5A4EZ44FRM4ASYMSZ3RHX2LT7A","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":"a10ea9a5767a42a60a984901e5a9a12d4ada424246a4c0eb34454a15778f0d29","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","title_canon_sha256":"15696678b98ae01eaf8116a712a260aa15b405b541ccf285290a8191f0a38f1f"},"schema_version":"1.0","source":{"id":"1905.11867","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11867","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11867v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11867","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"5A4EZ44FRM4A","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5A4EZ44FRM4ASYMS","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5A4EZ44F","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:d7597146a8dffd2edf512a91a690b4d00a711689c3efec7b0f7b928ba3346992","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":"We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner","authors_text":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","title":"Interactive Teaching Algorithms for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11867","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:f6ad7c0acc75bf8dc733478197b51434a7191cc58df1d83c9b4ba8fbef932db4","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":"a10ea9a5767a42a60a984901e5a9a12d4ada424246a4c0eb34454a15778f0d29","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","title_canon_sha256":"15696678b98ae01eaf8116a712a260aa15b405b541ccf285290a8191f0a38f1f"},"schema_version":"1.0","source":{"id":"1905.11867","kind":"arxiv","version":3}},"canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","first_computed_at":"2026-05-17T23:44:02.082131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:02.082131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B2B5qwU4mvOT3yBsZyYP1Knqg3K5RssfA9sPCWSh3AYqRVZ8yg5iF2Jo/ngDjYS+2wioD8PM4sMQlIBF+JS6Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:02.082638Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11867","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6ad7c0acc75bf8dc733478197b51434a7191cc58df1d83c9b4ba8fbef932db4","sha256:d7597146a8dffd2edf512a91a690b4d00a711689c3efec7b0f7b928ba3346992"],"state_sha256":"52b441314877b585067161ec66f9f5e926d0fa064ef10723298274e713945cea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/S5XAZgg4kBrPEbzu6amd35qTJDE7He1KbO2s/w1G9V3WZJHUHAqsbFRHbytj7U1S3zNBAUdckjae8dolXQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T00:39:23.325181Z","bundle_sha256":"95d83441bbe1b9563b9152780c3b0eac0a6437f4da608bcb440249babc61408b"}}