{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WYUOZUKJ23YYYE3N6T5IGTHUIZ","short_pith_number":"pith:WYUOZUKJ","canonical_record":{"source":{"id":"1902.07742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T19:22:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b2907c7d85295669642506f16e4fae875d36e93012943ba2e09f46d38192a3f2","abstract_canon_sha256":"3d115afb7d6ba24ea43a25a258d6993a29e130f60199229004e82d68d59a9ce4"},"schema_version":"1.0"},"canonical_sha256":"b628ecd149d6f18c136df4fa834cf446672640ef2485fa94fbbbb63536ed6767","source":{"kind":"arxiv","id":"1902.07742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07742","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07742v1","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07742","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"WYUOZUKJ23YY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WYUOZUKJ23YYYE3N","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WYUOZUKJ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WYUOZUKJ23YYYE3N6T5IGTHUIZ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T19:22:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b2907c7d85295669642506f16e4fae875d36e93012943ba2e09f46d38192a3f2","abstract_canon_sha256":"3d115afb7d6ba24ea43a25a258d6993a29e130f60199229004e82d68d59a9ce4"},"schema_version":"1.0"},"canonical_sha256":"b628ecd149d6f18c136df4fa834cf446672640ef2485fa94fbbbb63536ed6767","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:03.973429Z","signature_b64":"nCuXo399yTwN0ebULUk+4+bpA2KbVjPdcUj8/+cHi75h+iJcb2/CAd9J0ssurLl7cAZyV00Bf8rN3gQmjpOTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b628ecd149d6f18c136df4fa834cf446672640ef2485fa94fbbbb63536ed6767","last_reissued_at":"2026-05-17T23:53:03.972988Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:03.972988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07742","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":"2026-05-17T23:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5T95Fohmopkvo6HR1rCkgkOrIEmdYi45UGk9VOYWO47HYoEMybKVpS3GtTPDP4cI7/SPt06YUYKZYUV6guACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:22:30.091040Z"},"content_sha256":"72d487478f156d21b5d3490319626b9ee05e10c88e1effbfa0a50c33c339d06e","schema_version":"1.0","event_id":"sha256:72d487478f156d21b5d3490319626b9ee05e10c88e1effbfa0a50c33c339d06e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WYUOZUKJ23YYYE3N6T5IGTHUIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anoop Korattikara, Justin Fu, Sergey Levine, Sergio Guadarrama","submitted_at":"2019-02-20T19:22:00Z","abstract_excerpt":"Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward functions and goal states have been used to communicate objectives. But people can communicate objectives to each other simply by describing or demonstrating them. How can we build learning algorithms that will allow us to tell machines what we want them to do? In this work, we investiga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07742","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":"2026-05-17T23:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYD+bQmdxYIzzBbKZpuDUNUoOjVqlJ787vSsZBlc0VvLUNaCCepeXjSJNPfXd6qcre+tdLSlxILaN3ftY/VfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:22:30.091418Z"},"content_sha256":"89456c247afb19642542926e469fb22601e006b4b9a497c04de355dcb11d61af","schema_version":"1.0","event_id":"sha256:89456c247afb19642542926e469fb22601e006b4b9a497c04de355dcb11d61af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/bundle.json","state_url":"https://pith.science/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/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":"2026-06-05T10:22:30Z","links":{"resolver":"https://pith.science/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ","bundle":"https://pith.science/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/bundle.json","state":"https://pith.science/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYUOZUKJ23YYYE3N6T5IGTHUIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WYUOZUKJ23YYYE3N6T5IGTHUIZ","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":"3d115afb7d6ba24ea43a25a258d6993a29e130f60199229004e82d68d59a9ce4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T19:22:00Z","title_canon_sha256":"b2907c7d85295669642506f16e4fae875d36e93012943ba2e09f46d38192a3f2"},"schema_version":"1.0","source":{"id":"1902.07742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07742","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07742v1","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07742","created_at":"2026-05-17T23:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"WYUOZUKJ23YY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WYUOZUKJ23YYYE3N","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WYUOZUKJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:89456c247afb19642542926e469fb22601e006b4b9a497c04de355dcb11d61af","target":"graph","created_at":"2026-05-17T23:53:03Z","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":"Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward functions and goal states have been used to communicate objectives. But people can communicate objectives to each other simply by describing or demonstrating them. How can we build learning algorithms that will allow us to tell machines what we want them to do? In this work, we investiga","authors_text":"Anoop Korattikara, Justin Fu, Sergey Levine, Sergio Guadarrama","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T19:22:00Z","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07742","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":"sha256:72d487478f156d21b5d3490319626b9ee05e10c88e1effbfa0a50c33c339d06e","target":"record","created_at":"2026-05-17T23:53:03Z","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":"3d115afb7d6ba24ea43a25a258d6993a29e130f60199229004e82d68d59a9ce4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T19:22:00Z","title_canon_sha256":"b2907c7d85295669642506f16e4fae875d36e93012943ba2e09f46d38192a3f2"},"schema_version":"1.0","source":{"id":"1902.07742","kind":"arxiv","version":1}},"canonical_sha256":"b628ecd149d6f18c136df4fa834cf446672640ef2485fa94fbbbb63536ed6767","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b628ecd149d6f18c136df4fa834cf446672640ef2485fa94fbbbb63536ed6767","first_computed_at":"2026-05-17T23:53:03.972988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:03.972988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCuXo399yTwN0ebULUk+4+bpA2KbVjPdcUj8/+cHi75h+iJcb2/CAd9J0ssurLl7cAZyV00Bf8rN3gQmjpOTAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:03.973429Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d487478f156d21b5d3490319626b9ee05e10c88e1effbfa0a50c33c339d06e","sha256:89456c247afb19642542926e469fb22601e006b4b9a497c04de355dcb11d61af"],"state_sha256":"33325b35a3295d3533a06c6dbffd40063db2ccdae5b96f978576e81cb1f1adb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UUhmzc+c/wOeVD5Ov3UBD+bdUF5gC8UDcliRx/joT5OHjd+OXSKBrKvnT3jVVAXjB/x/Qwhp95pYLUi6L2iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T10:22:30.093344Z","bundle_sha256":"88f36487305300162f0b8819f0e1ff9cf08c9375ad09b15aa8690db8f044bc03"}}