{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BYLDLSG6MPCLN7F4MLJ5Y7GJYJ","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":"f62ffc1bab875270138a92055d38a684fac781176429ec593c268d7bcaf2c486","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-17T09:28:17Z","title_canon_sha256":"2e4da37392c0b632d7e3cbec380a9fa403e0f5952cf8c2fe01f3b9d04cab6555"},"schema_version":"1.0","source":{"id":"2104.08492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08492","created_at":"2026-07-05T02:32:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08492v1","created_at":"2026-07-05T02:32:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08492","created_at":"2026-07-05T02:32:52Z"},{"alias_kind":"pith_short_12","alias_value":"BYLDLSG6MPCL","created_at":"2026-07-05T02:32:52Z"},{"alias_kind":"pith_short_16","alias_value":"BYLDLSG6MPCLN7F4","created_at":"2026-07-05T02:32:52Z"},{"alias_kind":"pith_short_8","alias_value":"BYLDLSG6","created_at":"2026-07-05T02:32:52Z"}],"graph_snapshots":[{"event_id":"sha256:20032dc1f7479f44c5ad0e27a924927a5c87685204f1995161c9e5e361fee797","target":"graph","created_at":"2026-07-05T02:32:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.08492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we explore an auxiliary loss useful for reinforcement learning in environments where strong performing agents are required to be able to navigate a spatial environment. The auxiliary loss proposed is to minimize the classification error of a neural network classifier that predicts whether or not a pair of states sampled from the agents current episode trajectory are in order. The classifier takes as input a pair of states as well as the agent's memory. The motivation for this auxiliary loss is that there is a strong correlation with which of a pair of states is more recent in the ","authors_text":"Christian A. Schroeder de Witt, Eltayeb Ahmed, Luisa Zintgraf, Nicolas Usunier","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-17T09:28:17Z","title":"A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08492","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":"sha256:9ec8b4ca1b30c7df35d6abdf7fa2be0df022084d132ad8aebb124236f720e881","target":"record","created_at":"2026-07-05T02:32:52Z","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":"f62ffc1bab875270138a92055d38a684fac781176429ec593c268d7bcaf2c486","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-17T09:28:17Z","title_canon_sha256":"2e4da37392c0b632d7e3cbec380a9fa403e0f5952cf8c2fe01f3b9d04cab6555"},"schema_version":"1.0","source":{"id":"2104.08492","kind":"arxiv","version":1}},"canonical_sha256":"0e1635c8de63c4b6fcbc62d3dc7cc9c2423975e2a805202dd1f8b14b24e4bbe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e1635c8de63c4b6fcbc62d3dc7cc9c2423975e2a805202dd1f8b14b24e4bbe0","first_computed_at":"2026-07-05T02:32:52.546288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:52.546288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DsNp+sPfG53rjh1kzaG2e+Nn69nbCHN42VnFlihkILwL+dstFeBIonhIvXX0QdTUTu/zs0CgLSqhmHcDJaIWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:52.546783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ec8b4ca1b30c7df35d6abdf7fa2be0df022084d132ad8aebb124236f720e881","sha256:20032dc1f7479f44c5ad0e27a924927a5c87685204f1995161c9e5e361fee797"],"state_sha256":"2e82c7d76fa06a053230425d92f6583950b7be049a98a93638764f0a128019dd"}