{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ELMWG3LZBRNYVI2DENWYW3NRWU","short_pith_number":"pith:ELMWG3LZ","canonical_record":{"source":{"id":"1703.00727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"459038ceb0b5078be8301e6ecfafc7ab115a665e524e147cd559848c2f4e7801","abstract_canon_sha256":"6fa5cfb66a2d1b6c167de8a5083d749528507c5863ec4fea3b1c46c44b1a35e4"},"schema_version":"1.0"},"canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","source":{"kind":"arxiv","id":"1703.00727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00727","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00727v1","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00727","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"pith_short_12","alias_value":"ELMWG3LZBRNY","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"ELMWG3LZBRNYVI2D","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"ELMWG3LZ","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ELMWG3LZBRNYVI2DENWYW3NRWU","target":"record","payload":{"canonical_record":{"source":{"id":"1703.00727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"459038ceb0b5078be8301e6ecfafc7ab115a665e524e147cd559848c2f4e7801","abstract_canon_sha256":"6fa5cfb66a2d1b6c167de8a5083d749528507c5863ec4fea3b1c46c44b1a35e4"},"schema_version":"1.0"},"canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:40.947581Z","signature_b64":"oB7gZETZWJ3ym+1a2IGLaDl7xKGsKpYrMZ6t1OxAuj42XCUxB92zp1KdgwuONyfWmiTJnKfJMLo7NawHiFN/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","last_reissued_at":"2026-05-18T00:49:40.946890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:40.946890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.00727","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":"2026-05-18T00:49:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQlnMD2GUo20vZbvEU5fJmKKKwzhcVtFHVdLs/neg+EBMqT+7HW+fjuA01kKvjdbX1OTZQWApjd9VelJMB+AAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T07:15:14.005351Z"},"content_sha256":"e3ba40f2bd43bb5a6245f077cfb7241fe5ca0a758fb0ff6e551444ed7ec1b2d3","schema_version":"1.0","event_id":"sha256:e3ba40f2bd43bb5a6245f077cfb7241fe5ca0a758fb0ff6e551444ed7ec1b2d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ELMWG3LZBRNYVI2DENWYW3NRWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Predictive Policy Training using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, M\\r{a}rten Bj\\\"orkman","submitted_at":"2017-03-02T11:29:57Z","abstract_excerpt":"Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The percep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00727","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":"2026-05-18T00:49:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00sKDWmnDUk91pilmZnizcLjp5uNioA+tKYpo+nr/xOmmtwhbBu6G7TaFqbW0SXqgJFCh7pW6DiOmDuAU9wBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T07:15:14.005704Z"},"content_sha256":"fd59a5e92536cf23d803db3a0d05844a5e4e8fae50cd957fa6ca70940b2da84d","schema_version":"1.0","event_id":"sha256:fd59a5e92536cf23d803db3a0d05844a5e4e8fae50cd957fa6ca70940b2da84d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/bundle.json","state_url":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/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":"2026-06-23T07:15:14Z","links":{"resolver":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU","bundle":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/bundle.json","state":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ELMWG3LZBRNYVI2DENWYW3NRWU","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":"6fa5cfb66a2d1b6c167de8a5083d749528507c5863ec4fea3b1c46c44b1a35e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","title_canon_sha256":"459038ceb0b5078be8301e6ecfafc7ab115a665e524e147cd559848c2f4e7801"},"schema_version":"1.0","source":{"id":"1703.00727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00727","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00727v1","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00727","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"pith_short_12","alias_value":"ELMWG3LZBRNY","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"ELMWG3LZBRNYVI2D","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"ELMWG3LZ","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:fd59a5e92536cf23d803db3a0d05844a5e4e8fae50cd957fa6ca70940b2da84d","target":"graph","created_at":"2026-05-18T00:49:40Z","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":"Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The percep","authors_text":"Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, M\\r{a}rten Bj\\\"orkman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","title":"Deep Predictive Policy Training using Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00727","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:e3ba40f2bd43bb5a6245f077cfb7241fe5ca0a758fb0ff6e551444ed7ec1b2d3","target":"record","created_at":"2026-05-18T00:49:40Z","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":"6fa5cfb66a2d1b6c167de8a5083d749528507c5863ec4fea3b1c46c44b1a35e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","title_canon_sha256":"459038ceb0b5078be8301e6ecfafc7ab115a665e524e147cd559848c2f4e7801"},"schema_version":"1.0","source":{"id":"1703.00727","kind":"arxiv","version":1}},"canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","first_computed_at":"2026-05-18T00:49:40.946890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:40.946890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oB7gZETZWJ3ym+1a2IGLaDl7xKGsKpYrMZ6t1OxAuj42XCUxB92zp1KdgwuONyfWmiTJnKfJMLo7NawHiFN/AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:40.947581Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.00727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3ba40f2bd43bb5a6245f077cfb7241fe5ca0a758fb0ff6e551444ed7ec1b2d3","sha256:fd59a5e92536cf23d803db3a0d05844a5e4e8fae50cd957fa6ca70940b2da84d"],"state_sha256":"261c3b44910dd49e91e08ca846da9962e81c7af6439913445900a5bc64e090ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmQv92b12FPwNY/mLcqgNJ1QOjl9mltqUIFgXohyQLGgRZHtv5B4OsWnrR7AiNL6MyG1WHMy8Pzt8HNFVb5OCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T07:15:14.007806Z","bundle_sha256":"9eee67abc46fdaa57461596c9b0a4d7026db0e5097573b41654f211e8e87e69b"}}