{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BJWN3PGBDP2FV5NIC7LFYMU73Z","short_pith_number":"pith:BJWN3PGB","canonical_record":{"source":{"id":"1806.08479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"601d299fcd43b85e5a49ad983a033c794a49a520105922027e607b782f8f1b0f","abstract_canon_sha256":"3d0c23dd8a7207ebfeb9c677e8887731536d467dbb12855bca97bcd3be94a1ac"},"schema_version":"1.0"},"canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","source":{"kind":"arxiv","id":"1806.08479","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08479","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08479v1","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08479","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"BJWN3PGBDP2F","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BJWN3PGBDP2FV5NI","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BJWN3PGB","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BJWN3PGBDP2FV5NIC7LFYMU73Z","target":"record","payload":{"canonical_record":{"source":{"id":"1806.08479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"601d299fcd43b85e5a49ad983a033c794a49a520105922027e607b782f8f1b0f","abstract_canon_sha256":"3d0c23dd8a7207ebfeb9c677e8887731536d467dbb12855bca97bcd3be94a1ac"},"schema_version":"1.0"},"canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:37.138469Z","signature_b64":"EFnPRQhU87zJm9EHIuIxWxoGQSG33D60OkHblTdG38qP3rSxBKcKxGXZMblX5VB9O4g3tfO9LqRRA/TOzltFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","last_reissued_at":"2026-05-18T00:12:37.137872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:37.137872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.08479","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":"2026-05-18T00:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4n/5XGGipEXPlC2MA2Mzi1j7pX6O9gIRIpM/FD1YjE0ariGkvv760b7AVyZ5j4YxL9FB1TmeXAQ9KqXUXKdPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:24:44.440365Z"},"content_sha256":"c831b52c1e8dd66f5d2258593f5a0270809efb330bb64d98dc4057f7926c931c","schema_version":"1.0","event_id":"sha256:c831b52c1e8dd66f5d2258593f5a0270809efb330bb64d98dc4057f7926c931c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BJWN3PGBDP2FV5NIC7LFYMU73Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Eshed Ohn-Bar, Kris M. Kitani, Nicholas Rhinehart, Xinlei Pan, Yan Xu, Yilin Shen","submitted_at":"2018-06-22T03:24:00Z","abstract_excerpt":"Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08479","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":"2026-05-18T00:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncOuULWj6WYxzCOnBFIorM75Nb+PdfOeLt/mV00s4WLa8o2rJlDSDIp3i+52kOrxgbtcqD8UfMtWYYdXC/pvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:24:44.441024Z"},"content_sha256":"94469235baf8af0d7a0a040f798b6a3721f95d35b415d9e10802d45903792e48","schema_version":"1.0","event_id":"sha256:94469235baf8af0d7a0a040f798b6a3721f95d35b415d9e10802d45903792e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/bundle.json","state_url":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/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":"2026-05-30T14:24:44Z","links":{"resolver":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z","bundle":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/bundle.json","state":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BJWN3PGBDP2FV5NIC7LFYMU73Z","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":"3d0c23dd8a7207ebfeb9c677e8887731536d467dbb12855bca97bcd3be94a1ac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","title_canon_sha256":"601d299fcd43b85e5a49ad983a033c794a49a520105922027e607b782f8f1b0f"},"schema_version":"1.0","source":{"id":"1806.08479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08479","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08479v1","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08479","created_at":"2026-05-18T00:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"BJWN3PGBDP2F","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BJWN3PGBDP2FV5NI","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BJWN3PGB","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:94469235baf8af0d7a0a040f798b6a3721f95d35b415d9e10802d45903792e48","target":"graph","created_at":"2026-05-18T00:12:37Z","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"},"paper":{"abstract_excerpt":"Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal st","authors_text":"Eshed Ohn-Bar, Kris M. Kitani, Nicholas Rhinehart, Xinlei Pan, Yan Xu, Yilin Shen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","title":"Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08479","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:c831b52c1e8dd66f5d2258593f5a0270809efb330bb64d98dc4057f7926c931c","target":"record","created_at":"2026-05-18T00:12:37Z","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":"3d0c23dd8a7207ebfeb9c677e8887731536d467dbb12855bca97bcd3be94a1ac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","title_canon_sha256":"601d299fcd43b85e5a49ad983a033c794a49a520105922027e607b782f8f1b0f"},"schema_version":"1.0","source":{"id":"1806.08479","kind":"arxiv","version":1}},"canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","first_computed_at":"2026-05-18T00:12:37.137872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:37.137872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EFnPRQhU87zJm9EHIuIxWxoGQSG33D60OkHblTdG38qP3rSxBKcKxGXZMblX5VB9O4g3tfO9LqRRA/TOzltFAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:37.138469Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.08479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c831b52c1e8dd66f5d2258593f5a0270809efb330bb64d98dc4057f7926c931c","sha256:94469235baf8af0d7a0a040f798b6a3721f95d35b415d9e10802d45903792e48"],"state_sha256":"80c8ab14adc9d72b23f4a2a48e8f5233c2827c91b33d6ac71a92d6ad70747633"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9R/7I5NgX192g/Q71vdaxbGV6yvUMQ46+DqFF5//kaNbBaWECJyaUzc88oFaNJJwIlSu8cCJuejCcIVImRVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:24:44.443938Z","bundle_sha256":"8b41ee78a56920d1d966f5139d80d0001388314b424dc938337ba41b09c0bbb2"}}