{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GKJWYLIGPXC7FAGUMVFA54XBWG","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":"0a94e252267dde19e0f17ad9b84f2859a56d34b44b6a51575bea508bb75ea1de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:50:16Z","title_canon_sha256":"63806c9b267d66589ed7f0238568ae464666ca821f5ea908552c312cfad87176"},"schema_version":"1.0","source":{"id":"2405.00662","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00662","created_at":"2026-07-05T09:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00662v3","created_at":"2026-07-05T09:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00662","created_at":"2026-07-05T09:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"GKJWYLIGPXC7","created_at":"2026-07-05T09:38:14Z"},{"alias_kind":"pith_short_16","alias_value":"GKJWYLIGPXC7FAGU","created_at":"2026-07-05T09:38:14Z"},{"alias_kind":"pith_short_8","alias_value":"GKJWYLIG","created_at":"2026-07-05T09:38:14Z"}],"graph_snapshots":[{"event_id":"sha256:0b46ec154d7a92d507e2f3028d84c62a9a72eaa7396ef08ceab560e652a04844","target":"graph","created_at":"2026-07-05T09:38:14Z","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/2405.00662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting new targets. However, previous works have observed that networks trained under non-stationarity exhibit an inability to continue learning, termed loss of plasticity, and eventually a collapse in performance. For off-policy deep value-based RL methods, this phenomenon has been correlated with a decrease in representation rank and the ability to","authors_text":"Andrea Miele, Caglar Gulcehre, Daniil Pyatko, Razvan Pascanu, Skander Moalla","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:50:16Z","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00662","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:af58e824b4a2067c7b2732b003090243bcf2252c6bbe264c576d209c31bd1664","target":"record","created_at":"2026-07-05T09:38:14Z","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":"0a94e252267dde19e0f17ad9b84f2859a56d34b44b6a51575bea508bb75ea1de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:50:16Z","title_canon_sha256":"63806c9b267d66589ed7f0238568ae464666ca821f5ea908552c312cfad87176"},"schema_version":"1.0","source":{"id":"2405.00662","kind":"arxiv","version":3}},"canonical_sha256":"32936c2d067dc5f280d4654a0ef2e1b1bcc540521b210a79f7a874606e2e099c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32936c2d067dc5f280d4654a0ef2e1b1bcc540521b210a79f7a874606e2e099c","first_computed_at":"2026-07-05T09:38:14.882224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:14.882224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j9VG8KNAIl+34XZhlX+cNuYOcVL2ndWs8Su41ZuQJ5Y/WExvemkjKgxgmiFNDj+WJxjigEPiPKV7gCX7e64QBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:14.882580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00662","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af58e824b4a2067c7b2732b003090243bcf2252c6bbe264c576d209c31bd1664","sha256:0b46ec154d7a92d507e2f3028d84c62a9a72eaa7396ef08ceab560e652a04844"],"state_sha256":"9763424c602edf547a81b1dfb3610cf862c387ab379a1a833b9a9e2685bc2f3c"}