{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AHHN4CJMSELT46Z4IQ2WEXL6GB","short_pith_number":"pith:AHHN4CJM","canonical_record":{"source":{"id":"1705.05035","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-14T22:53:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d0651a7b1c0c1808aa5ee97ccafc852abd9aff32be95cb61da15470f0781d615","abstract_canon_sha256":"f4795963bc81c3c8ceab63c5ece98a6043d45ff4ebbdab8bccefb6cc3cedff80"},"schema_version":"1.0"},"canonical_sha256":"01cede092c91173e7b3c4435625d7e305a25af7181174f8b2bdcd654d072d194","source":{"kind":"arxiv","id":"1705.05035","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.05035","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1705.05035v3","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05035","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"AHHN4CJMSELT","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AHHN4CJMSELT46Z4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AHHN4CJM","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AHHN4CJMSELT46Z4IQ2WEXL6GB","target":"record","payload":{"canonical_record":{"source":{"id":"1705.05035","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-14T22:53:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d0651a7b1c0c1808aa5ee97ccafc852abd9aff32be95cb61da15470f0781d615","abstract_canon_sha256":"f4795963bc81c3c8ceab63c5ece98a6043d45ff4ebbdab8bccefb6cc3cedff80"},"schema_version":"1.0"},"canonical_sha256":"01cede092c91173e7b3c4435625d7e305a25af7181174f8b2bdcd654d072d194","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:54.172565Z","signature_b64":"F+c9IHZj65MGvbhlHdRkt0mD8avwH27PpWqiTbCEvu6n3LjVsK9t/XyDgkNcU/3FHZ+Uhqrd1pbzASZnn44YAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01cede092c91173e7b3c4435625d7e305a25af7181174f8b2bdcd654d072d194","last_reissued_at":"2026-05-17T23:43:54.171949Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:54.171949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.05035","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":"2026-05-17T23:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZNn7nSJ8uyqlxVYgb6dzVEKKF+yqo7Fyfoo4BmrZbpFwAGE4VQUlRAv8fGlpnSRMP5qtpww5Vgc7ALipIlrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T21:35:40.384854Z"},"content_sha256":"a70eeafb6961a8c8318acdcc181ff881a6d2c5f685c628cac2672e976a9390e4","schema_version":"1.0","event_id":"sha256:a70eeafb6961a8c8318acdcc181ff881a6d2c5f685c628cac2672e976a9390e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AHHN4CJMSELT46Z4IQ2WEXL6GB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Davidson, Julian Ibarz, Luke Metz, Navdeep Jaitly","submitted_at":"2017-05-14T22:53:13Z","abstract_excerpt":"It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequence-to-sequence models for structured prediction problems to develop policies over discretized spaces. Central to this method is the realization that complex functions over high dimensional spaces can be modeled by neural networks that predict one dimension at a time. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05035","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":""},"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":"2026-05-17T23:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NciXpxAsQWSotfLSbLL2fFW5ctRE+BjZLJJUwzi625xoyTM7WT1M3dkMq6+L/crqILaRyGNB2BqPCJsI57f9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T21:35:40.385343Z"},"content_sha256":"6ba853397606a4e283f14ad48c3661727ca8d9c5fc9e8d76f81280395272116d","schema_version":"1.0","event_id":"sha256:6ba853397606a4e283f14ad48c3661727ca8d9c5fc9e8d76f81280395272116d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/bundle.json","state_url":"https://pith.science/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/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":"2026-06-03T21:35:40Z","links":{"resolver":"https://pith.science/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB","bundle":"https://pith.science/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/bundle.json","state":"https://pith.science/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHHN4CJMSELT46Z4IQ2WEXL6GB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AHHN4CJMSELT46Z4IQ2WEXL6GB","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":"f4795963bc81c3c8ceab63c5ece98a6043d45ff4ebbdab8bccefb6cc3cedff80","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-14T22:53:13Z","title_canon_sha256":"d0651a7b1c0c1808aa5ee97ccafc852abd9aff32be95cb61da15470f0781d615"},"schema_version":"1.0","source":{"id":"1705.05035","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.05035","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1705.05035v3","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05035","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"AHHN4CJMSELT","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AHHN4CJMSELT46Z4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AHHN4CJM","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:6ba853397606a4e283f14ad48c3661727ca8d9c5fc9e8d76f81280395272116d","target":"graph","created_at":"2026-05-17T23:43:54Z","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":"It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequence-to-sequence models for structured prediction problems to develop policies over discretized spaces. Central to this method is the realization that complex functions over high dimensional spaces can be modeled by neural networks that predict one dimension at a time. Specifical","authors_text":"James Davidson, Julian Ibarz, Luke Metz, Navdeep Jaitly","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-14T22:53:13Z","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05035","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:a70eeafb6961a8c8318acdcc181ff881a6d2c5f685c628cac2672e976a9390e4","target":"record","created_at":"2026-05-17T23:43:54Z","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":"f4795963bc81c3c8ceab63c5ece98a6043d45ff4ebbdab8bccefb6cc3cedff80","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-14T22:53:13Z","title_canon_sha256":"d0651a7b1c0c1808aa5ee97ccafc852abd9aff32be95cb61da15470f0781d615"},"schema_version":"1.0","source":{"id":"1705.05035","kind":"arxiv","version":3}},"canonical_sha256":"01cede092c91173e7b3c4435625d7e305a25af7181174f8b2bdcd654d072d194","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01cede092c91173e7b3c4435625d7e305a25af7181174f8b2bdcd654d072d194","first_computed_at":"2026-05-17T23:43:54.171949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:54.171949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F+c9IHZj65MGvbhlHdRkt0mD8avwH27PpWqiTbCEvu6n3LjVsK9t/XyDgkNcU/3FHZ+Uhqrd1pbzASZnn44YAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:54.172565Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.05035","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a70eeafb6961a8c8318acdcc181ff881a6d2c5f685c628cac2672e976a9390e4","sha256:6ba853397606a4e283f14ad48c3661727ca8d9c5fc9e8d76f81280395272116d"],"state_sha256":"6cfb4a3e8925d10c69a930f72a1bbdc8a6104b97d596442077a198b6282cc43b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"syNbJCObD6rxuasGiRiWH2UFnXJf0nfwL7uWysDF0EdFK22pZNDXrC0xnX1/nntHf5jn+FLf4dVrME0VEINqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T21:35:40.396823Z","bundle_sha256":"5b87e2438140c0053acb4ef4d1aad96a0982979b86fd98d72cd089ce4bdaf851"}}