{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GEARHQZCPI2FRIAPE6AE7Z43JW","short_pith_number":"pith:GEARHQZC","canonical_record":{"source":{"id":"2012.08824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-16T09:46:58Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"f98f5b592b8cd832e428db5eabb403a79eabe9c956442db9ecadcdd3e66238b9","abstract_canon_sha256":"325a42c959855d9d94fa4f4726e5dd7d25d3dd6eb201bd8559768c5152ac0b4f"},"schema_version":"1.0"},"canonical_sha256":"310113c3227a3458a00f27804fe79b4d90481b2e344ef5caac924eb257646354","source":{"kind":"arxiv","id":"2012.08824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08824","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08824v1","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08824","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"GEARHQZCPI2F","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"GEARHQZCPI2FRIAP","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"GEARHQZC","created_at":"2026-07-05T02:00:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GEARHQZCPI2FRIAPE6AE7Z43JW","target":"record","payload":{"canonical_record":{"source":{"id":"2012.08824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-16T09:46:58Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"f98f5b592b8cd832e428db5eabb403a79eabe9c956442db9ecadcdd3e66238b9","abstract_canon_sha256":"325a42c959855d9d94fa4f4726e5dd7d25d3dd6eb201bd8559768c5152ac0b4f"},"schema_version":"1.0"},"canonical_sha256":"310113c3227a3458a00f27804fe79b4d90481b2e344ef5caac924eb257646354","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:03.850058Z","signature_b64":"O/ElEzlJdNrgewzm81+E4STmr9hlsDDgmWxzVUGKHbsdeshFazTxpTAAmMKYSr/rXtqi9jwchN9mn1jEJe66Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"310113c3227a3458a00f27804fe79b4d90481b2e344ef5caac924eb257646354","last_reissued_at":"2026-07-05T02:00:03.849536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:03.849536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.08824","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":"2026-07-05T02:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dduIhPuC3B9e0Lzy4lIgMxQDG/vGbO/gIwOiJ/hlFh2x0fOkOFSJAyGLTli2q7xyYktFwITBQbtCJkgihOUFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:20:42.953749Z"},"content_sha256":"e959f14c683ee8f5f8cff06199c4a2aa47afcb0462b9568410cdbd6192a9ec44","schema_version":"1.0","event_id":"sha256:e959f14c683ee8f5f8cff06199c4a2aa47afcb0462b9568410cdbd6192a9ec44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GEARHQZCPI2FRIAPE6AE7Z43JW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandra Malysheva, Aleksei Shpilman, Daniel Kudenko","submitted_at":"2020-12-16T09:46:58Z","abstract_excerpt":"Learning to produce efficient movement behaviour for humanoid robots from scratch is a hard problem, as has been illustrated by the \"Learning to run\" competition at NIPS 2017. The goal of this competition was to train a two-legged model of a humanoid body to run in a simulated race course with maximum speed. All submissions took a tabula rasa approach to reinforcement learning (RL) and were able to produce relatively fast, but not optimal running behaviour. In this paper, we demonstrate how data from videos of human running (e.g. taken from YouTube) can be used to shape the reward of the human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08824","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/2012.08824/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":"2026-07-05T02:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MM3s/Q8JMqJNppV13LUfpJMnlx5Ie02E+l31cVLuJuHL2a5A/1VTwdihu9hbXRowdk/+2frGtIfn7gzqrQU2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:20:42.954135Z"},"content_sha256":"021d1b0aa68987ff26f2eaf80a5822ea53e6b95a826df3501422f6b4133f220d","schema_version":"1.0","event_id":"sha256:021d1b0aa68987ff26f2eaf80a5822ea53e6b95a826df3501422f6b4133f220d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/bundle.json","state_url":"https://pith.science/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/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":"2026-07-24T02:20:42Z","links":{"resolver":"https://pith.science/pith/GEARHQZCPI2FRIAPE6AE7Z43JW","bundle":"https://pith.science/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/bundle.json","state":"https://pith.science/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEARHQZCPI2FRIAPE6AE7Z43JW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GEARHQZCPI2FRIAPE6AE7Z43JW","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":"325a42c959855d9d94fa4f4726e5dd7d25d3dd6eb201bd8559768c5152ac0b4f","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-16T09:46:58Z","title_canon_sha256":"f98f5b592b8cd832e428db5eabb403a79eabe9c956442db9ecadcdd3e66238b9"},"schema_version":"1.0","source":{"id":"2012.08824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08824","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08824v1","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08824","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"GEARHQZCPI2F","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"GEARHQZCPI2FRIAP","created_at":"2026-07-05T02:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"GEARHQZC","created_at":"2026-07-05T02:00:03Z"}],"graph_snapshots":[{"event_id":"sha256:021d1b0aa68987ff26f2eaf80a5822ea53e6b95a826df3501422f6b4133f220d","target":"graph","created_at":"2026-07-05T02:00:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.08824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to produce efficient movement behaviour for humanoid robots from scratch is a hard problem, as has been illustrated by the \"Learning to run\" competition at NIPS 2017. The goal of this competition was to train a two-legged model of a humanoid body to run in a simulated race course with maximum speed. All submissions took a tabula rasa approach to reinforcement learning (RL) and were able to produce relatively fast, but not optimal running behaviour. In this paper, we demonstrate how data from videos of human running (e.g. taken from YouTube) can be used to shape the reward of the human","authors_text":"Aleksandra Malysheva, Aleksei Shpilman, Daniel Kudenko","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-16T09:46:58Z","title":"Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08824","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:e959f14c683ee8f5f8cff06199c4a2aa47afcb0462b9568410cdbd6192a9ec44","target":"record","created_at":"2026-07-05T02:00:03Z","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":"325a42c959855d9d94fa4f4726e5dd7d25d3dd6eb201bd8559768c5152ac0b4f","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-16T09:46:58Z","title_canon_sha256":"f98f5b592b8cd832e428db5eabb403a79eabe9c956442db9ecadcdd3e66238b9"},"schema_version":"1.0","source":{"id":"2012.08824","kind":"arxiv","version":1}},"canonical_sha256":"310113c3227a3458a00f27804fe79b4d90481b2e344ef5caac924eb257646354","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"310113c3227a3458a00f27804fe79b4d90481b2e344ef5caac924eb257646354","first_computed_at":"2026-07-05T02:00:03.849536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:03.849536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O/ElEzlJdNrgewzm81+E4STmr9hlsDDgmWxzVUGKHbsdeshFazTxpTAAmMKYSr/rXtqi9jwchN9mn1jEJe66Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:03.850058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e959f14c683ee8f5f8cff06199c4a2aa47afcb0462b9568410cdbd6192a9ec44","sha256:021d1b0aa68987ff26f2eaf80a5822ea53e6b95a826df3501422f6b4133f220d"],"state_sha256":"9f6f5e101e7ecf812a2be251640d145ce63708bb3006c97a641c6d1ea60470d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qmfb7hXqJG+qU7CVwXFkFEfCk3VdamRepEwoUpab6GNFG7GbV1Y0pK5z425HiMqr6/XVjL3UjqwrhQx8sJnjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T02:20:42.956770Z","bundle_sha256":"f519793e7f5261df79ee116954a3846e922e8d175b4b8e8f2da4b25c1a86cc08"}}