{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QFEI5DX5FCOSZGETGESZV25WWU","short_pith_number":"pith:QFEI5DX5","canonical_record":{"source":{"id":"2005.11810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"181b0b37bb237d131141efb4f6ad5d9f4eddfd58c58107d6d10ccfb647a751c8","abstract_canon_sha256":"8d3fad7f03ab71288d963864304ab4319988e862e9bcb9327cb55aead17e7134"},"schema_version":"1.0"},"canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","source":{"kind":"arxiv","id":"2005.11810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.11810","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2005.11810v1","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11810","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"QFEI5DX5FCOS","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"QFEI5DX5FCOSZGET","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"QFEI5DX5","created_at":"2026-07-05T01:05:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QFEI5DX5FCOSZGETGESZV25WWU","target":"record","payload":{"canonical_record":{"source":{"id":"2005.11810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"181b0b37bb237d131141efb4f6ad5d9f4eddfd58c58107d6d10ccfb647a751c8","abstract_canon_sha256":"8d3fad7f03ab71288d963864304ab4319988e862e9bcb9327cb55aead17e7134"},"schema_version":"1.0"},"canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:28.460135Z","signature_b64":"3oIaXUxRgRi8oaYo2I3vYjHN9QP0vUEKUBYp2UVmRI5Ou/5FlOvBOj+PZiLAZTq2pvQylC2lbUkMvcdHQfZ8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","last_reissued_at":"2026-07-05T01:05:28.459636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:28.459636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.11810","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":"2026-07-05T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzRwMo6R1tW/uqEYysrKvZ18Mcbih/3OpAt1P+F1I0b3ErErgjRDgVxKXObsvyKE8NVLjhExYHe4nKwvyqkXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:17:27.226319Z"},"content_sha256":"1865a50cb44c36a5e5116eb5c7455c33cb3fd89b7fe598c7fdc46d8a5f6dfdb4","schema_version":"1.0","event_id":"sha256:1865a50cb44c36a5e5116eb5c7455c33cb3fd89b7fe598c7fdc46d8a5f6dfdb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QFEI5DX5FCOSZGETGESZV25WWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning visual servo policies via planner cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kate Saenko, Robert Platt, Ulrich Viereck","submitted_at":"2020-05-24T17:56:57Z","abstract_excerpt":"Learning control policies for visual servoing in novel environments is an important problem. However, standard model-free policy learning methods are slow. This paper explores planner cloning: using behavior cloning to learn policies that mimic the behavior of a full-state motion planner in simulation. We propose Penalized Q Cloning (PQC), a new behavior cloning algorithm. We show that it outperforms several baselines and ablations on some challenging problems involving visual servoing in novel environments while avoiding obstacles. Finally, we demonstrate that these policies can be transferre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11810","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.11810/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":"2026-07-05T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RxIg63dx/OgowR4lix2AUp5qPueRnHhE0w92y1S3OwRnvuuNDdpL6oyb3ekRN7kmxPh4TH6CYZ+Bi/EEoXSDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:17:27.229948Z"},"content_sha256":"1f09f8f4c5f358d0e56134e9f03e193c3edadf04e1bcc11b018cd387f72f62c9","schema_version":"1.0","event_id":"sha256:1f09f8f4c5f358d0e56134e9f03e193c3edadf04e1bcc11b018cd387f72f62c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/bundle.json","state_url":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFEI5DX5FCOSZGETGESZV25WWU/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":"2026-08-05T13:17:27Z","links":{"resolver":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU","bundle":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/bundle.json","state":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFEI5DX5FCOSZGETGESZV25WWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QFEI5DX5FCOSZGETGESZV25WWU","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":"8d3fad7f03ab71288d963864304ab4319988e862e9bcb9327cb55aead17e7134","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","title_canon_sha256":"181b0b37bb237d131141efb4f6ad5d9f4eddfd58c58107d6d10ccfb647a751c8"},"schema_version":"1.0","source":{"id":"2005.11810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.11810","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2005.11810v1","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11810","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"QFEI5DX5FCOS","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"QFEI5DX5FCOSZGET","created_at":"2026-07-05T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"QFEI5DX5","created_at":"2026-07-05T01:05:28Z"}],"graph_snapshots":[{"event_id":"sha256:1f09f8f4c5f358d0e56134e9f03e193c3edadf04e1bcc11b018cd387f72f62c9","target":"graph","created_at":"2026-07-05T01:05:28Z","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/2005.11810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning control policies for visual servoing in novel environments is an important problem. However, standard model-free policy learning methods are slow. This paper explores planner cloning: using behavior cloning to learn policies that mimic the behavior of a full-state motion planner in simulation. We propose Penalized Q Cloning (PQC), a new behavior cloning algorithm. We show that it outperforms several baselines and ablations on some challenging problems involving visual servoing in novel environments while avoiding obstacles. Finally, we demonstrate that these policies can be transferre","authors_text":"Kate Saenko, Robert Platt, Ulrich Viereck","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","title":"Learning visual servo policies via planner cloning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11810","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":"sha256:1865a50cb44c36a5e5116eb5c7455c33cb3fd89b7fe598c7fdc46d8a5f6dfdb4","target":"record","created_at":"2026-07-05T01:05:28Z","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":"8d3fad7f03ab71288d963864304ab4319988e862e9bcb9327cb55aead17e7134","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","title_canon_sha256":"181b0b37bb237d131141efb4f6ad5d9f4eddfd58c58107d6d10ccfb647a751c8"},"schema_version":"1.0","source":{"id":"2005.11810","kind":"arxiv","version":1}},"canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","first_computed_at":"2026-07-05T01:05:28.459636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:28.459636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3oIaXUxRgRi8oaYo2I3vYjHN9QP0vUEKUBYp2UVmRI5Ou/5FlOvBOj+PZiLAZTq2pvQylC2lbUkMvcdHQfZ8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:28.460135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.11810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1865a50cb44c36a5e5116eb5c7455c33cb3fd89b7fe598c7fdc46d8a5f6dfdb4","sha256:1f09f8f4c5f358d0e56134e9f03e193c3edadf04e1bcc11b018cd387f72f62c9"],"state_sha256":"99a5b4ffc7790531a2e44aad241b27dbf09e4bd9c390c45815ffc376ab69e888"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prKiMNNrsfIYQyyru+LkhfcyBod8kdGDcidHF8pTxtp1yNttoAMZKG2UpQcxy41qfHUpvwmieKLkh0hqN70ICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:17:27.249582Z","bundle_sha256":"c4c76682ef2d118272b6c8a3e83a619799327db9a1ea29732cf369b617bd64d6"}}