{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:3ZHSQ2I6R3T37ETVTNX6OJSO3M","short_pith_number":"pith:3ZHSQ2I6","canonical_record":{"source":{"id":"1511.06581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"ace1e6d10a3703390b2d84cd1eacb674f97ae5bf67b657945645a79cc2cb1fbb","abstract_canon_sha256":"c9ce4af50cbca545fef340d09a714e990e6197db0d28bf47bf31436f03186e5a"},"schema_version":"1.0"},"canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","source":{"kind":"arxiv","id":"1511.06581","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06581","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06581v3","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06581","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"3ZHSQ2I6R3T3","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3ZHSQ2I6R3T37ETV","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3ZHSQ2I6","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:3ZHSQ2I6R3T37ETVTNX6OJSO3M","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"ace1e6d10a3703390b2d84cd1eacb674f97ae5bf67b657945645a79cc2cb1fbb","abstract_canon_sha256":"c9ce4af50cbca545fef340d09a714e990e6197db0d28bf47bf31436f03186e5a"},"schema_version":"1.0"},"canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:46.933996Z","signature_b64":"NZaNw1N+lpK/yw3v8oLMP+8KL8AsQh6CB1XcLgbSUWgP+hpxDYpQdju3V6G51lUeDsYU4o0E2H2ifRsVVDESCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","last_reissued_at":"2026-05-18T01:17:46.933061Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:46.933061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06581","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":"2026-05-18T01:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eb8H/csnjGXv/voqR8UYe5+yzovGbpPndfxBMCxsAU1ElJdKUp2tXQ3M2cRFyy9PML5aH+F4bZgNQbkuKlwlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T19:14:04.542094Z"},"content_sha256":"d34f42b6ccaf434ee9856ed690c69be49b7fc4ed54c78037979aa423ed5a04ed","schema_version":"1.0","event_id":"sha256:d34f42b6ccaf434ee9856ed690c69be49b7fc4ed54c78037979aa423ed5a04ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:3ZHSQ2I6R3T37ETVTNX6OJSO3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dueling Network Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, Marc Lanctot, Matteo Hessel, Nando de Freitas, Tom Schaul, Ziyu Wang","submitted_at":"2015-11-20T13:07:54Z","abstract_excerpt":"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying rein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06581","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":"2026-05-18T01:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nOx0zNVFQOAfb/99yZBY1erJCAocu2SffLFAsHj2FO3GBn8UVTlSKypccHmFSF9YWih+El0gEPB2WnvSV+NiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T19:14:04.542832Z"},"content_sha256":"fe69f238a0059b95362c1adaf247fdc2991a0dfb1d0e44fbddd33d988c3eb2c3","schema_version":"1.0","event_id":"sha256:fe69f238a0059b95362c1adaf247fdc2991a0dfb1d0e44fbddd33d988c3eb2c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/bundle.json","state_url":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/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":"2026-05-18T19:14:04Z","links":{"resolver":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M","bundle":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/bundle.json","state":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3ZHSQ2I6R3T37ETVTNX6OJSO3M","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":"c9ce4af50cbca545fef340d09a714e990e6197db0d28bf47bf31436f03186e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","title_canon_sha256":"ace1e6d10a3703390b2d84cd1eacb674f97ae5bf67b657945645a79cc2cb1fbb"},"schema_version":"1.0","source":{"id":"1511.06581","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06581","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06581v3","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06581","created_at":"2026-05-18T01:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"3ZHSQ2I6R3T3","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3ZHSQ2I6R3T37ETV","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3ZHSQ2I6","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:fe69f238a0059b95362c1adaf247fdc2991a0dfb1d0e44fbddd33d988c3eb2c3","target":"graph","created_at":"2026-05-18T01:17:46Z","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":"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying rein","authors_text":"Hado van Hasselt, Marc Lanctot, Matteo Hessel, Nando de Freitas, Tom Schaul, Ziyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","title":"Dueling Network Architectures for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06581","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:d34f42b6ccaf434ee9856ed690c69be49b7fc4ed54c78037979aa423ed5a04ed","target":"record","created_at":"2026-05-18T01:17:46Z","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":"c9ce4af50cbca545fef340d09a714e990e6197db0d28bf47bf31436f03186e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","title_canon_sha256":"ace1e6d10a3703390b2d84cd1eacb674f97ae5bf67b657945645a79cc2cb1fbb"},"schema_version":"1.0","source":{"id":"1511.06581","kind":"arxiv","version":3}},"canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","first_computed_at":"2026-05-18T01:17:46.933061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:46.933061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZaNw1N+lpK/yw3v8oLMP+8KL8AsQh6CB1XcLgbSUWgP+hpxDYpQdju3V6G51lUeDsYU4o0E2H2ifRsVVDESCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:46.933996Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06581","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d34f42b6ccaf434ee9856ed690c69be49b7fc4ed54c78037979aa423ed5a04ed","sha256:fe69f238a0059b95362c1adaf247fdc2991a0dfb1d0e44fbddd33d988c3eb2c3"],"state_sha256":"1868e1c56ec7ee1d5dac13279999cbdfbedc9450d7f1f982191fad901f59e528"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZUzFmARnKrINgqBQy2AVb3FqNwPjeuA6d64ZpnLFYyDPFsAk0fTj34B/SmxAcfHJGT1Ylx5DXgJbcMesnkeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T19:14:04.544885Z","bundle_sha256":"970f5901e923929b46947e04d28fc27abcaa3fdf17b6454c377fcf2d0d7afebc"}}