{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ONR2HWIIKC4IOWOBHZACS6WGV4","short_pith_number":"pith:ONR2HWII","schema_version":"1.0","canonical_sha256":"7363a3d90850b88759c13e40297ac6af2570e93f8fa51183bf882be0f1b40526","source":{"kind":"arxiv","id":"2605.31273","version":1},"attestation_state":"computed","paper":{"title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fabian Schramm, Franki Nguimatsia-Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","submitted_at":"2026-05-29T13:05:08Z","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"},"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":"2605.31273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:05:08Z","cross_cats_sorted":[],"title_canon_sha256":"61a116c95a980c06eeda8b2eafe7337d5df25405c867c7c59cb2db5dda9d5547","abstract_canon_sha256":"1d4afb09a22a876d8f270431fe7a085c5878e7440f677e7e3e9ea4723d7a666d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:08.190707Z","signature_b64":"JKrM+Y36/jR80n+pS0JcCPrJuiUhgj3SKmud3UmPXKobFP5l1vKKVgWjp13Zvw1JvvQyJnmVSZOSbeqIkL0vBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7363a3d90850b88759c13e40297ac6af2570e93f8fa51183bf882be0f1b40526","last_reissued_at":"2026-06-01T01:04:08.189749Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:08.189749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fabian Schramm, Franki Nguimatsia-Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","submitted_at":"2026-05-29T13:05:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31273","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.31273/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":"2605.31273","created_at":"2026-06-01T01:04:08.189919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31273v1","created_at":"2026-06-01T01:04:08.189919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31273","created_at":"2026-06-01T01:04:08.189919+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONR2HWIIKC4I","created_at":"2026-06-01T01:04:08.189919+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONR2HWIIKC4IOWOB","created_at":"2026-06-01T01:04:08.189919+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONR2HWII","created_at":"2026-06-01T01:04:08.189919+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/ONR2HWIIKC4IOWOBHZACS6WGV4","json":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4.json","graph_json":"https://pith.science/api/pith-number/ONR2HWIIKC4IOWOBHZACS6WGV4/graph.json","events_json":"https://pith.science/api/pith-number/ONR2HWIIKC4IOWOBHZACS6WGV4/events.json","paper":"https://pith.science/paper/ONR2HWII"},"agent_actions":{"view_html":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4","download_json":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4.json","view_paper":"https://pith.science/paper/ONR2HWII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31273&json=true","fetch_graph":"https://pith.science/api/pith-number/ONR2HWIIKC4IOWOBHZACS6WGV4/graph.json","fetch_events":"https://pith.science/api/pith-number/ONR2HWIIKC4IOWOBHZACS6WGV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4/action/storage_attestation","attest_author":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4/action/author_attestation","sign_citation":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4/action/citation_signature","submit_replication":"https://pith.science/pith/ONR2HWIIKC4IOWOBHZACS6WGV4/action/replication_record"}},"created_at":"2026-06-01T01:04:08.189919+00:00","updated_at":"2026-06-01T01:04:08.189919+00:00"}