{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:TLDAE4I26GZVXLI4BKM6J22ZOT","short_pith_number":"pith:TLDAE4I2","canonical_record":{"source":{"id":"1602.02658","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:27:31Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"dd741a41fc2b8b400a93de5941ea837bfaf67c6638d3a4ebbece8bbed418aebf","abstract_canon_sha256":"a1fb8f9bcc34f333598bcb9d195605ab4dbba8614dd5bb11bc3eb212b9cd8136"},"schema_version":"1.0"},"canonical_sha256":"9ac602711af1b35bad1c0a99e4eb5974fe854b6bc6bea2fb9229dbc8f8c6af51","source":{"kind":"arxiv","id":"1602.02658","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02658","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02658v4","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02658","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"pith_short_12","alias_value":"TLDAE4I26GZV","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"TLDAE4I26GZVXLI4","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"TLDAE4I2","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:TLDAE4I26GZVXLI4BKM6J22ZOT","target":"record","payload":{"canonical_record":{"source":{"id":"1602.02658","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:27:31Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"dd741a41fc2b8b400a93de5941ea837bfaf67c6638d3a4ebbece8bbed418aebf","abstract_canon_sha256":"a1fb8f9bcc34f333598bcb9d195605ab4dbba8614dd5bb11bc3eb212b9cd8136"},"schema_version":"1.0"},"canonical_sha256":"9ac602711af1b35bad1c0a99e4eb5974fe854b6bc6bea2fb9229dbc8f8c6af51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:54.493612Z","signature_b64":"AeefYWRYjMVRYm77c2prDvdamY+R7Jr0mZAdhhPYrg9UvwEI+okC0Q8f3RLuv8DkcwGUHWhZ6rIwJPdyBid3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ac602711af1b35bad1c0a99e4eb5974fe854b6bc6bea2fb9229dbc8f8c6af51","last_reissued_at":"2026-05-18T00:45:54.493014Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:54.493014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.02658","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":"2026-05-18T00:45:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FuXE2IAO2Ln+zSYFnJ7LGPdhUO+X3NzhxXLDUvgu+MDZVwqeGciur9Nv8063+MCb7nkDwjp7pwrcXsft582JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:20:03.259203Z"},"content_sha256":"d1b9acd4b930fe97479c91f8b347e89a4c115efaa09652529ee2117f5c8edde9","schema_version":"1.0","event_id":"sha256:d1b9acd4b930fe97479c91f8b347e89a4c115efaa09652529ee2117f5c8edde9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:TLDAE4I26GZVXLI4BKM6J22ZOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graying the black box: Understanding DQNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Nir Ben Zrihem, Shie Mannor, Tom Zahavy","submitted_at":"2016-02-08T17:27:31Z","abstract_excerpt":"In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us to identify spatio-temporal abstractions directly from features and may be used as a sub-goal detector in future work. Using our tools we reveal that the features learned by DQNs aggregate the state space in a hierarchical fashion,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02658","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":""},"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":"2026-05-18T00:45:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8Z62ykaaNJ6yYYLdxIkeRFN9Ro/HvsIBam+cjXXUXhavelCfbzqhotzN5uVkn/HP67Xf28WzPSwp+TPtg6LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:20:03.260113Z"},"content_sha256":"48dde361cc9802ee49bd1643c43ef3b07ccf277ca5a78bc3377b003fa61a44cf","schema_version":"1.0","event_id":"sha256:48dde361cc9802ee49bd1643c43ef3b07ccf277ca5a78bc3377b003fa61a44cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/bundle.json","state_url":"https://pith.science/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/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":"2026-05-31T08:20:03Z","links":{"resolver":"https://pith.science/pith/TLDAE4I26GZVXLI4BKM6J22ZOT","bundle":"https://pith.science/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/bundle.json","state":"https://pith.science/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLDAE4I26GZVXLI4BKM6J22ZOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:TLDAE4I26GZVXLI4BKM6J22ZOT","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":"a1fb8f9bcc34f333598bcb9d195605ab4dbba8614dd5bb11bc3eb212b9cd8136","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:27:31Z","title_canon_sha256":"dd741a41fc2b8b400a93de5941ea837bfaf67c6638d3a4ebbece8bbed418aebf"},"schema_version":"1.0","source":{"id":"1602.02658","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02658","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02658v4","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02658","created_at":"2026-05-18T00:45:54Z"},{"alias_kind":"pith_short_12","alias_value":"TLDAE4I26GZV","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"TLDAE4I26GZVXLI4","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"TLDAE4I2","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:48dde361cc9802ee49bd1643c43ef3b07ccf277ca5a78bc3377b003fa61a44cf","target":"graph","created_at":"2026-05-18T00:45:54Z","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":"In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us to identify spatio-temporal abstractions directly from features and may be used as a sub-goal detector in future work. Using our tools we reveal that the features learned by DQNs aggregate the state space in a hierarchical fashion,","authors_text":"Nir Ben Zrihem, Shie Mannor, Tom Zahavy","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:27:31Z","title":"Graying the black box: Understanding DQNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02658","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:d1b9acd4b930fe97479c91f8b347e89a4c115efaa09652529ee2117f5c8edde9","target":"record","created_at":"2026-05-18T00:45:54Z","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":"a1fb8f9bcc34f333598bcb9d195605ab4dbba8614dd5bb11bc3eb212b9cd8136","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:27:31Z","title_canon_sha256":"dd741a41fc2b8b400a93de5941ea837bfaf67c6638d3a4ebbece8bbed418aebf"},"schema_version":"1.0","source":{"id":"1602.02658","kind":"arxiv","version":4}},"canonical_sha256":"9ac602711af1b35bad1c0a99e4eb5974fe854b6bc6bea2fb9229dbc8f8c6af51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ac602711af1b35bad1c0a99e4eb5974fe854b6bc6bea2fb9229dbc8f8c6af51","first_computed_at":"2026-05-18T00:45:54.493014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:54.493014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AeefYWRYjMVRYm77c2prDvdamY+R7Jr0mZAdhhPYrg9UvwEI+okC0Q8f3RLuv8DkcwGUHWhZ6rIwJPdyBid3BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:54.493612Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.02658","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1b9acd4b930fe97479c91f8b347e89a4c115efaa09652529ee2117f5c8edde9","sha256:48dde361cc9802ee49bd1643c43ef3b07ccf277ca5a78bc3377b003fa61a44cf"],"state_sha256":"a749162ff2388197d48f663a5b44fa8081e4ad4651ea3b0b2449cbcbbc5f072e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8n52seHgXUewXeb+zIJakGjJ4UspV5uqHcutiRC3B35H8/vSz6XX8iWjODlTPMqUtB9o5jEU66ZbrxUT23ymCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T08:20:03.262990Z","bundle_sha256":"d3345cfcdc5ccc25fab82495b762a4dc6b52cb79b4bf37020a41a29d32fb390b"}}