{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LBDT4MOYHIWNWKQAJF63UEYIKC","short_pith_number":"pith:LBDT4MOY","canonical_record":{"source":{"id":"1901.07186","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T06:46:19Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"83507c18700af70e823a1c2fdb837387e481f4b075a78a63d1d1816bbe016f5b","abstract_canon_sha256":"36992905bef20e32aed82432e4daaaac576799a6cead51abba4016fe9231bddf"},"schema_version":"1.0"},"canonical_sha256":"58473e31d83a2cdb2a00497dba130850b80c208a3dca65f83f6c35f743b8e1e7","source":{"kind":"arxiv","id":"1901.07186","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07186","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07186v4","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07186","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"LBDT4MOYHIWN","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"LBDT4MOYHIWNWKQA","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"LBDT4MOY","created_at":"2026-07-05T06:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LBDT4MOYHIWNWKQAJF63UEYIKC","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07186","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T06:46:19Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"83507c18700af70e823a1c2fdb837387e481f4b075a78a63d1d1816bbe016f5b","abstract_canon_sha256":"36992905bef20e32aed82432e4daaaac576799a6cead51abba4016fe9231bddf"},"schema_version":"1.0"},"canonical_sha256":"58473e31d83a2cdb2a00497dba130850b80c208a3dca65f83f6c35f743b8e1e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:22.440234Z","signature_b64":"eJj/sUu7EdQ4/dMFxDFDoIT+qONScDsvgN5epuhv27drivXvJQzi/a7AXakc++Wvg6WcuD2+ND77VEkC+S1KAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58473e31d83a2cdb2a00497dba130850b80c208a3dca65f83f6c35f743b8e1e7","last_reissued_at":"2026-07-05T06:30:22.439707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:22.439707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07186","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PH+AdSP14yZBy+XkM7c5yLPhdwAfRMyF+oY4Unaq1W65BamjK1RsobBrvZDf8OVWvKCRO0zXfpS0+Ca7e5vCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:28:41.113540Z"},"content_sha256":"15b515751c627f38176683866ad3df29ef97bdd79fd53b0001ad8feee913d89d","schema_version":"1.0","event_id":"sha256:15b515751c627f38176683866ad3df29ef97bdd79fd53b0001ad8feee913d89d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LBDT4MOYHIWNWKQAJF63UEYIKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Learning to Imitate from a Single Video Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Pal, Florian Golemo, Glen Berseth","submitted_at":"2019-01-22T06:46:19Z","abstract_excerpt":"Agents that can learn to imitate given video observation -- \\emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration. We use a Siamese recurrent neural network architecture to learn rewards in space and time between motion clips while training an RL policy to minimize this distance. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07186","kind":"arxiv","version":4},"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/1901.07186/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":"2026-07-05T06:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmGzgK6UbniYfSr8g0OETuVqbEuqNVivIXYMW8EHN2qf1Ldvnc+Dv6zSDsUINL1t8FYWTEJAQpVNns1FIExwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:28:41.114102Z"},"content_sha256":"c03f9e1cd9365c1f9e9cfce3d2093392c7314c9a98e6cd37f2301173daba6fa9","schema_version":"1.0","event_id":"sha256:c03f9e1cd9365c1f9e9cfce3d2093392c7314c9a98e6cd37f2301173daba6fa9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/bundle.json","state_url":"https://pith.science/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/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":"2026-08-23T10:28:41Z","links":{"resolver":"https://pith.science/pith/LBDT4MOYHIWNWKQAJF63UEYIKC","bundle":"https://pith.science/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/bundle.json","state":"https://pith.science/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBDT4MOYHIWNWKQAJF63UEYIKC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LBDT4MOYHIWNWKQAJF63UEYIKC","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":"36992905bef20e32aed82432e4daaaac576799a6cead51abba4016fe9231bddf","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T06:46:19Z","title_canon_sha256":"83507c18700af70e823a1c2fdb837387e481f4b075a78a63d1d1816bbe016f5b"},"schema_version":"1.0","source":{"id":"1901.07186","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07186","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07186v4","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07186","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"LBDT4MOYHIWN","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"LBDT4MOYHIWNWKQA","created_at":"2026-07-05T06:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"LBDT4MOY","created_at":"2026-07-05T06:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:c03f9e1cd9365c1f9e9cfce3d2093392c7314c9a98e6cd37f2301173daba6fa9","target":"graph","created_at":"2026-07-05T06:30:22Z","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/1901.07186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents that can learn to imitate given video observation -- \\emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration. We use a Siamese recurrent neural network architecture to learn rewards in space and time between motion clips while training an RL policy to minimize this distance. Th","authors_text":"Christopher Pal, Florian Golemo, Glen Berseth","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T06:46:19Z","title":"Towards Learning to Imitate from a Single Video Demonstration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07186","kind":"arxiv","version":4},"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":"sha256:15b515751c627f38176683866ad3df29ef97bdd79fd53b0001ad8feee913d89d","target":"record","created_at":"2026-07-05T06:30:22Z","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":"36992905bef20e32aed82432e4daaaac576799a6cead51abba4016fe9231bddf","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T06:46:19Z","title_canon_sha256":"83507c18700af70e823a1c2fdb837387e481f4b075a78a63d1d1816bbe016f5b"},"schema_version":"1.0","source":{"id":"1901.07186","kind":"arxiv","version":4}},"canonical_sha256":"58473e31d83a2cdb2a00497dba130850b80c208a3dca65f83f6c35f743b8e1e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58473e31d83a2cdb2a00497dba130850b80c208a3dca65f83f6c35f743b8e1e7","first_computed_at":"2026-07-05T06:30:22.439707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:22.439707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eJj/sUu7EdQ4/dMFxDFDoIT+qONScDsvgN5epuhv27drivXvJQzi/a7AXakc++Wvg6WcuD2+ND77VEkC+S1KAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:22.440234Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07186","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15b515751c627f38176683866ad3df29ef97bdd79fd53b0001ad8feee913d89d","sha256:c03f9e1cd9365c1f9e9cfce3d2093392c7314c9a98e6cd37f2301173daba6fa9"],"state_sha256":"5c5620bb8139d06f91f8a545cd94cc319f828c4299e44f0c523bbefdd97ac0d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ASSwGvCFGxppmZRo3Mb9USl35s8zPQ66F33BukzhtsAQ5kENik6oymU6Lq9+eiFOFMe27rCadFfxrIGYy0xBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:28:41.117834Z","bundle_sha256":"84e3aafa33d3b619152443cb4aeb0e12580b8363c132fdc2c3cab9784d1027bb"}}