{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:2UCSZK3J3OFV6CKINZUSWZH4LY","short_pith_number":"pith:2UCSZK3J","canonical_record":{"source":{"id":"1606.07112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-22T21:18:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cbf4a7d9d31e5ac1653376eeff01e4a1449e415bf7c6636143be947f100adcd0","abstract_canon_sha256":"775b263609d4c4582ec98e7884361617839b0390d95cc6f060045abd36316b4a"},"schema_version":"1.0"},"canonical_sha256":"d5052cab69db8b5f09486e692b64fc5e3065fce96423ce8f93ec6137bef91a0d","source":{"kind":"arxiv","id":"1606.07112","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07112","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07112v1","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07112","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"2UCSZK3J3OFV","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2UCSZK3J3OFV6CKI","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2UCSZK3J","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:2UCSZK3J3OFV6CKINZUSWZH4LY","target":"record","payload":{"canonical_record":{"source":{"id":"1606.07112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-22T21:18:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cbf4a7d9d31e5ac1653376eeff01e4a1449e415bf7c6636143be947f100adcd0","abstract_canon_sha256":"775b263609d4c4582ec98e7884361617839b0390d95cc6f060045abd36316b4a"},"schema_version":"1.0"},"canonical_sha256":"d5052cab69db8b5f09486e692b64fc5e3065fce96423ce8f93ec6137bef91a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:58.649182Z","signature_b64":"/JwLlM9C2UCrRnFmkbi9GJuuPPXL+A/xzs4c1qXIefkGxQypcYruSGcbsBHb4o6Rvf3GOmLytUq6ISJtPniTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5052cab69db8b5f09486e692b64fc5e3065fce96423ce8f93ec6137bef91a0d","last_reissued_at":"2026-05-18T01:11:58.648814Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:58.648814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.07112","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":"2026-05-18T01:11:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNp5LoZhAI+xI0xVZZY4ocQxcrc+pe3seTizci1TlNnKb6aCHcbmgLwHffBYE5Y03KqpLtsUIZvXEvjVYJB6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:25:13.886086Z"},"content_sha256":"db1e0a8bbaf1bdd567c9880d4ef351871e897e90cb13cc5669870f3860f50588","schema_version":"1.0","event_id":"sha256:db1e0a8bbaf1bdd567c9880d4ef351871e897e90cb13cc5669870f3860f50588"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:2UCSZK3J3OFV6CKINZUSWZH4LY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visualizing Dynamics: from t-SNE to SEMI-MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Nir Ben Zrihem, Shie Mannor, Tom Zahavy","submitted_at":"2016-06-22T21:18:50Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions that they learn. In this paper, we present a novel method that automatically discovers an internal Semi Markov Decision Process (SMDP) model in the Deep Q Network's (DQN) learned representation. We suggest a novel visualization method that represents the SMDP model by a directed g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07112","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":"2026-05-18T01:11:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RG1x/Qx0nxtvZCOeLXPrwmfPmqIO2kPoDLXULe3IMTGVt6J5DM+NosSRZ9ZupD35P22lsxLqhE6sREaiTce4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:25:13.886451Z"},"content_sha256":"1349d23237b69be14c072b0c79c1469d3dcaf9944a694a9623e712f217c30410","schema_version":"1.0","event_id":"sha256:1349d23237b69be14c072b0c79c1469d3dcaf9944a694a9623e712f217c30410"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/bundle.json","state_url":"https://pith.science/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/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":"2026-05-31T00:25:13Z","links":{"resolver":"https://pith.science/pith/2UCSZK3J3OFV6CKINZUSWZH4LY","bundle":"https://pith.science/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/bundle.json","state":"https://pith.science/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2UCSZK3J3OFV6CKINZUSWZH4LY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:2UCSZK3J3OFV6CKINZUSWZH4LY","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":"775b263609d4c4582ec98e7884361617839b0390d95cc6f060045abd36316b4a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-22T21:18:50Z","title_canon_sha256":"cbf4a7d9d31e5ac1653376eeff01e4a1449e415bf7c6636143be947f100adcd0"},"schema_version":"1.0","source":{"id":"1606.07112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07112","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07112v1","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07112","created_at":"2026-05-18T01:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"2UCSZK3J3OFV","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2UCSZK3J3OFV6CKI","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2UCSZK3J","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:1349d23237b69be14c072b0c79c1469d3dcaf9944a694a9623e712f217c30410","target":"graph","created_at":"2026-05-18T01:11:58Z","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":"Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions that they learn. In this paper, we present a novel method that automatically discovers an internal Semi Markov Decision Process (SMDP) model in the Deep Q Network's (DQN) learned representation. We suggest a novel visualization method that represents the SMDP model by a directed g","authors_text":"Nir Ben Zrihem, Shie Mannor, Tom Zahavy","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-22T21:18:50Z","title":"Visualizing Dynamics: from t-SNE to SEMI-MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07112","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:db1e0a8bbaf1bdd567c9880d4ef351871e897e90cb13cc5669870f3860f50588","target":"record","created_at":"2026-05-18T01:11:58Z","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":"775b263609d4c4582ec98e7884361617839b0390d95cc6f060045abd36316b4a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-22T21:18:50Z","title_canon_sha256":"cbf4a7d9d31e5ac1653376eeff01e4a1449e415bf7c6636143be947f100adcd0"},"schema_version":"1.0","source":{"id":"1606.07112","kind":"arxiv","version":1}},"canonical_sha256":"d5052cab69db8b5f09486e692b64fc5e3065fce96423ce8f93ec6137bef91a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5052cab69db8b5f09486e692b64fc5e3065fce96423ce8f93ec6137bef91a0d","first_computed_at":"2026-05-18T01:11:58.648814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:58.648814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JwLlM9C2UCrRnFmkbi9GJuuPPXL+A/xzs4c1qXIefkGxQypcYruSGcbsBHb4o6Rvf3GOmLytUq6ISJtPniTBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:58.649182Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.07112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db1e0a8bbaf1bdd567c9880d4ef351871e897e90cb13cc5669870f3860f50588","sha256:1349d23237b69be14c072b0c79c1469d3dcaf9944a694a9623e712f217c30410"],"state_sha256":"7469ed4dad26b60556fc79d85d5e46c26f23175a26f6234eeb2554ef37b5f561"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddNBS4YkpWyKpyus3r81Q2RIxPwujYbIkcr4ZGzGxWTVrzvMpirh4dGSQQAd6C4Er1INoWPxjw28KgsSnu36Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T00:25:13.888453Z","bundle_sha256":"200f7481576ab45dd7da39b5cbdf3f5cc60fae3f74c17519133f3042fcd8a9d9"}}