{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ONR2HWIIKC4IOWOBHZACS6WGV4","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":"1d4afb09a22a876d8f270431fe7a085c5878e7440f677e7e3e9ea4723d7a666d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:05:08Z","title_canon_sha256":"61a116c95a980c06eeda8b2eafe7337d5df25405c867c7c59cb2db5dda9d5547"},"schema_version":"1.0","source":{"id":"2605.31273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31273","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31273v1","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31273","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"ONR2HWIIKC4I","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"ONR2HWIIKC4IOWOB","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"ONR2HWII","created_at":"2026-06-01T01:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:694b05bed8899f0dbc2d86d210571cb7aba593db6436faee9ae38b76ba88cdbb","target":"graph","created_at":"2026-06-01T01:04:08Z","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/2605.31273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 layers, scaled CRL still struggles with long-horizon goal-conditioned planning due to the uniformity-tolerance dilemma inherent in contrastive losses. We introduce Survival Reinforcement Learning (SRL), an online classification-based alternative that extends the survival value learning framework by maximizing the agent's dwell time at target goals. SRL bypasses the structural constraints of CRL and mitigates the \"bang-bang\" control solutions inhere","authors_text":"Fabian Schramm, Franki Nguimatsia-Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:05:08Z","title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31273","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":"sha256:0ac0e87085f6754938a43b0ea644618a7cbe854a3e82ac3a1ad6877eeb596e1b","target":"record","created_at":"2026-06-01T01:04:08Z","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":"1d4afb09a22a876d8f270431fe7a085c5878e7440f677e7e3e9ea4723d7a666d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:05:08Z","title_canon_sha256":"61a116c95a980c06eeda8b2eafe7337d5df25405c867c7c59cb2db5dda9d5547"},"schema_version":"1.0","source":{"id":"2605.31273","kind":"arxiv","version":1}},"canonical_sha256":"7363a3d90850b88759c13e40297ac6af2570e93f8fa51183bf882be0f1b40526","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7363a3d90850b88759c13e40297ac6af2570e93f8fa51183bf882be0f1b40526","first_computed_at":"2026-06-01T01:04:08.189749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:08.189749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JKrM+Y36/jR80n+pS0JcCPrJuiUhgj3SKmud3UmPXKobFP5l1vKKVgWjp13Zvw1JvvQyJnmVSZOSbeqIkL0vBw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:08.190707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ac0e87085f6754938a43b0ea644618a7cbe854a3e82ac3a1ad6877eeb596e1b","sha256:694b05bed8899f0dbc2d86d210571cb7aba593db6436faee9ae38b76ba88cdbb"],"state_sha256":"aa428b6fe7849a93687646065f2b4ba70d52eb66caef1b7c823b0f775e24e581"}