{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A6ZLAZOWCNVTTMOTNLQD35HSDX","short_pith_number":"pith:A6ZLAZOW","canonical_record":{"source":{"id":"1906.05838","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T17:39:52Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"f9fa1c180f090a5802d4b23b5a8a41a454d005d2906ab65ee8dba99f4b881bcc","abstract_canon_sha256":"21bccae31acc5577be087e9abac376e4a28e6417991d14d83321e6ee38829348"},"schema_version":"1.0"},"canonical_sha256":"07b2b065d6136b39b1d36ae03df4f21dcee256c234059bce612b7ded0d5886a1","source":{"kind":"arxiv","id":"1906.05838","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05838","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05838v3","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05838","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZLAZOWCNVT","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZLAZOWCNVTTMOT","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZLAZOW","created_at":"2026-07-05T01:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A6ZLAZOWCNVTTMOTNLQD35HSDX","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05838","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T17:39:52Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"f9fa1c180f090a5802d4b23b5a8a41a454d005d2906ab65ee8dba99f4b881bcc","abstract_canon_sha256":"21bccae31acc5577be087e9abac376e4a28e6417991d14d83321e6ee38829348"},"schema_version":"1.0"},"canonical_sha256":"07b2b065d6136b39b1d36ae03df4f21dcee256c234059bce612b7ded0d5886a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:07.936663Z","signature_b64":"XjuMOWtkSNG2BPpwJmW8BUShaV06gvXGPw6iuRHr1Jabtdm4LpeD/sN0en5Vo47aCD6x+ZwTXquCV0HfEYuFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b2b065d6136b39b1d36ae03df4f21dcee256c234059bce612b7ded0d5886a1","last_reissued_at":"2026-07-05T01:06:07.936171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:07.936171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05838","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":"2026-07-05T01:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xg9jub2WfvRUNz7hFO1fuX66gV39EU6Y6KjzgePPGt4fE25hpt2yLoPPP3WDnUD5aQPg+Gro9qNI869K2b19CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:08:06.447132Z"},"content_sha256":"ad24d1b07f2a37a47c74ad46b07827f4badf3f9ba9c27b09780cf0fc778e33b1","schema_version":"1.0","event_id":"sha256:ad24d1b07f2a37a47c74ad46b07827f4badf3f9ba9c27b09780cf0fc778e33b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A6ZLAZOWCNVTTMOTNLQD35HSDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-conditioned Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlos Florensa, Mariano Phielipp, Pieter Abbeel, Yiming Ding","submitted_at":"2019-06-13T17:39:52Z","abstract_excerpt":"Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where detecting whether the desired configuration is reached might require considerable supervision and instrumentation. Furthermore, we are often interested in being able to reach a wide range of configurations, hence setting up a different reward every time might be unpractical. Methods like Hindsight Experience Replay (HER) have recently shown promise to learn polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05838","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/1906.05838/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":"2026-07-05T01:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grfgEPicmwNWSue0EkIxe3iJ+O1E3QmZTj6/VhiFRIyAi5SRrtKq0/Ap0INU1YzEc+/AorQVBnAolckxmygIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:08:06.447678Z"},"content_sha256":"0a227f0d994651de88397e916f017b77a2905cccd9dc9c5df78051654611b971","schema_version":"1.0","event_id":"sha256:0a227f0d994651de88397e916f017b77a2905cccd9dc9c5df78051654611b971"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/bundle.json","state_url":"https://pith.science/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/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":"2026-08-09T12:08:06Z","links":{"resolver":"https://pith.science/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX","bundle":"https://pith.science/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/bundle.json","state":"https://pith.science/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6ZLAZOWCNVTTMOTNLQD35HSDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A6ZLAZOWCNVTTMOTNLQD35HSDX","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":"21bccae31acc5577be087e9abac376e4a28e6417991d14d83321e6ee38829348","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T17:39:52Z","title_canon_sha256":"f9fa1c180f090a5802d4b23b5a8a41a454d005d2906ab65ee8dba99f4b881bcc"},"schema_version":"1.0","source":{"id":"1906.05838","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05838","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05838v3","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05838","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZLAZOWCNVT","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZLAZOWCNVTTMOT","created_at":"2026-07-05T01:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZLAZOW","created_at":"2026-07-05T01:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:0a227f0d994651de88397e916f017b77a2905cccd9dc9c5df78051654611b971","target":"graph","created_at":"2026-07-05T01:06:07Z","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/1906.05838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where detecting whether the desired configuration is reached might require considerable supervision and instrumentation. Furthermore, we are often interested in being able to reach a wide range of configurations, hence setting up a different reward every time might be unpractical. Methods like Hindsight Experience Replay (HER) have recently shown promise to learn polic","authors_text":"Carlos Florensa, Mariano Phielipp, Pieter Abbeel, Yiming Ding","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T17:39:52Z","title":"Goal-conditioned Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05838","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:ad24d1b07f2a37a47c74ad46b07827f4badf3f9ba9c27b09780cf0fc778e33b1","target":"record","created_at":"2026-07-05T01:06:07Z","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":"21bccae31acc5577be087e9abac376e4a28e6417991d14d83321e6ee38829348","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T17:39:52Z","title_canon_sha256":"f9fa1c180f090a5802d4b23b5a8a41a454d005d2906ab65ee8dba99f4b881bcc"},"schema_version":"1.0","source":{"id":"1906.05838","kind":"arxiv","version":3}},"canonical_sha256":"07b2b065d6136b39b1d36ae03df4f21dcee256c234059bce612b7ded0d5886a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07b2b065d6136b39b1d36ae03df4f21dcee256c234059bce612b7ded0d5886a1","first_computed_at":"2026-07-05T01:06:07.936171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:07.936171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XjuMOWtkSNG2BPpwJmW8BUShaV06gvXGPw6iuRHr1Jabtdm4LpeD/sN0en5Vo47aCD6x+ZwTXquCV0HfEYuFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:07.936663Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05838","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad24d1b07f2a37a47c74ad46b07827f4badf3f9ba9c27b09780cf0fc778e33b1","sha256:0a227f0d994651de88397e916f017b77a2905cccd9dc9c5df78051654611b971"],"state_sha256":"4ad51b13f3d54b40e710f4ec4ccd6aac5f8f19d7bb7c18cdcd3d57ed52e9e201"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksICyrHi3QcONHaFzVDcZVvrmAiyIfv/CgGu5mz1DTCcKeMyr8u7lUtT/6mJQfsTqJ9pljXFskKSYd8o9AjhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:08:06.452752Z","bundle_sha256":"f4e9bc2e278a1e22ded3344702d95c6795a11a5be3ab528afcf287e135bf9e77"}}