{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KB5Y6X5UF2EB6BUELDEEEBHEN2","short_pith_number":"pith:KB5Y6X5U","schema_version":"1.0","canonical_sha256":"507b8f5fb42e881f068458c84204e46eae844a53c8970413f8fe26d40c69402d","source":{"kind":"arxiv","id":"2006.02252","version":2},"attestation_state":"computed","paper":{"title":"Interferobot: aligning an optical interferometer by a reinforcement learning agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.optics"],"primary_cat":"cs.RO","authors_text":"Alexander Lvovsky, Alexander Ulanov, Dmitry Sorokin, Ekaterina Sazhina","submitted_at":"2020-06-03T13:10:54Z","abstract_excerpt":"Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots. Here we train an RL agent to align a Mach-Zehnder interferometer, which is an essential part of many optical experiments, based on images of interference fringes acquired by a monocular camera. The agent is trained in a simulated environment, without any hand-coded features or a priori information about the physics, and subsequently transferred to a physical interferometer. Thanks to a set of domain randomizations simulating uncertainties in p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.02252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-03T13:10:54Z","cross_cats_sorted":["cs.LG","physics.optics"],"title_canon_sha256":"872f37922539e8473cce4a1d3731473d09c9e19ce44088b19df4f86cd201aca4","abstract_canon_sha256":"ebe15c50b34297847e9b969df582a536c794c4f931e7a25cf3ca7386b1017dfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:29.443467Z","signature_b64":"FAZK7oCVvbYGlVs1kMJb00oI+LHs+T8IDotl4XYkIQqfR5pF8RTr5GMay8kZsXvzkZ647PLLUNDPu14qEw5sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507b8f5fb42e881f068458c84204e46eae844a53c8970413f8fe26d40c69402d","last_reissued_at":"2026-07-05T02:24:29.443045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:29.443045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interferobot: aligning an optical interferometer by a reinforcement learning agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.optics"],"primary_cat":"cs.RO","authors_text":"Alexander Lvovsky, Alexander Ulanov, Dmitry Sorokin, Ekaterina Sazhina","submitted_at":"2020-06-03T13:10:54Z","abstract_excerpt":"Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots. Here we train an RL agent to align a Mach-Zehnder interferometer, which is an essential part of many optical experiments, based on images of interference fringes acquired by a monocular camera. The agent is trained in a simulated environment, without any hand-coded features or a priori information about the physics, and subsequently transferred to a physical interferometer. Thanks to a set of domain randomizations simulating uncertainties in p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02252","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.02252/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.02252","created_at":"2026-07-05T02:24:29.443108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02252v2","created_at":"2026-07-05T02:24:29.443108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02252","created_at":"2026-07-05T02:24:29.443108+00:00"},{"alias_kind":"pith_short_12","alias_value":"KB5Y6X5UF2EB","created_at":"2026-07-05T02:24:29.443108+00:00"},{"alias_kind":"pith_short_16","alias_value":"KB5Y6X5UF2EB6BUE","created_at":"2026-07-05T02:24:29.443108+00:00"},{"alias_kind":"pith_short_8","alias_value":"KB5Y6X5U","created_at":"2026-07-05T02:24:29.443108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2","json":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2.json","graph_json":"https://pith.science/api/pith-number/KB5Y6X5UF2EB6BUELDEEEBHEN2/graph.json","events_json":"https://pith.science/api/pith-number/KB5Y6X5UF2EB6BUELDEEEBHEN2/events.json","paper":"https://pith.science/paper/KB5Y6X5U"},"agent_actions":{"view_html":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2","download_json":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2.json","view_paper":"https://pith.science/paper/KB5Y6X5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02252&json=true","fetch_graph":"https://pith.science/api/pith-number/KB5Y6X5UF2EB6BUELDEEEBHEN2/graph.json","fetch_events":"https://pith.science/api/pith-number/KB5Y6X5UF2EB6BUELDEEEBHEN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2/action/storage_attestation","attest_author":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2/action/author_attestation","sign_citation":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2/action/citation_signature","submit_replication":"https://pith.science/pith/KB5Y6X5UF2EB6BUELDEEEBHEN2/action/replication_record"}},"created_at":"2026-07-05T02:24:29.443108+00:00","updated_at":"2026-07-05T02:24:29.443108+00:00"}