{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GKQNBDK55JPUUBGJCH7YG32B2X","short_pith_number":"pith:GKQNBDK5","schema_version":"1.0","canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","source":{"kind":"arxiv","id":"2604.17551","version":2},"attestation_state":"computed","paper":{"title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"The goal-conditioned value function equals a discounted sum of survival probabilities over time.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fabian Schramm, Franki Nguimatsia Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","submitted_at":"2026-04-19T17:44:13Z","abstract_excerpt":"Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While recent work has explored contrastive and supervised formulations to improve stability, we present a probabilistic alternative, called survival value learning (SVL), that reframes GCRL as a survival learning problem by modeling the time-to-goal from each state as a probability distribution. This structured distributional Monte Carlo perspective yields a closed-form identity that expresses the goal-conditioned value fun"},"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":"2604.17551","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T17:44:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f04d9c29ff742410496f820d3317476e16e695943603766e5c0b1f5f7a2caf1","abstract_canon_sha256":"323de9196b25189805225d400185f8b287b6edc59cc055c7230178f9eca48999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:53.316224Z","signature_b64":"1pV1AGqF+uFJrrXr7hhwa9jYM+MaP52fUpNrm962fNdzJEYkF3q5SSEFi4sjndc7I5tvWXJdhR/g7jegUd70Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","last_reissued_at":"2026-06-01T01:03:53.315040Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:53.315040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"The goal-conditioned value function equals a discounted sum of survival probabilities over time.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fabian Schramm, Franki Nguimatsia Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","submitted_at":"2026-04-19T17:44:13Z","abstract_excerpt":"Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While recent work has explored contrastive and supervised formulations to improve stability, we present a probabilistic alternative, called survival value learning (SVL), that reframes GCRL as a survival learning problem by modeling the time-to-goal from each state as a probability distribution. This structured distributional Monte Carlo perspective yields a closed-form identity that expresses the goal-conditioned value fun"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This structured distributional Monte Carlo perspective yields a closed-form identity that expresses the goal-conditioned value function as a discounted sum of survival probabilities, enabling value estimation via a hazard model trained via maximum likelihood on both event and right-censored trajectories.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modeling time-to-goal as a probability distribution via a hazard function produces stable value estimates that avoid the bootstrapping instability of temporal-difference methods, and that the three practical estimators (finite-horizon truncation and binned infinite-horizon approximations) faithfully capture long-horizon objectives without introducing significant bias.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Survival value learning expresses the goal-conditioned value function as a discounted sum of survival probabilities and estimates it with maximum-likelihood hazard models on censored data, matching or exceeding TD baselines on long-horizon offline GCRL tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The goal-conditioned value function equals a discounted sum of survival probabilities over time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dda31e33a9c284b4b49ad1db146bed5e837c368ecaf7f8737bada6382368ed50"},"source":{"id":"2604.17551","kind":"arxiv","version":2},"verdict":{"id":"369fb219-d8d7-47ec-8b27-61441b58355b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:41:08.833872Z","strongest_claim":"This structured distributional Monte Carlo perspective yields a closed-form identity that expresses the goal-conditioned value function as a discounted sum of survival probabilities, enabling value estimation via a hazard model trained via maximum likelihood on both event and right-censored trajectories.","one_line_summary":"Survival value learning expresses the goal-conditioned value function as a discounted sum of survival probabilities and estimates it with maximum-likelihood hazard models on censored data, matching or exceeding TD baselines on long-horizon offline GCRL tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modeling time-to-goal as a probability distribution via a hazard function produces stable value estimates that avoid the bootstrapping instability of temporal-difference methods, and that the three practical estimators (finite-horizon truncation and binned infinite-horizon approximations) faithfully capture long-horizon objectives without introducing significant bias.","pith_extraction_headline":"The goal-conditioned value function equals a discounted sum of survival probabilities over time."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17551/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":"2604.17551","created_at":"2026-06-01T01:03:53.315209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17551v2","created_at":"2026-06-01T01:03:53.315209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17551","created_at":"2026-06-01T01:03:53.315209+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKQNBDK55JPU","created_at":"2026-06-01T01:03:53.315209+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKQNBDK55JPUUBGJ","created_at":"2026-06-01T01:03:53.315209+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKQNBDK5","created_at":"2026-06-01T01:03:53.315209+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/GKQNBDK55JPUUBGJCH7YG32B2X","json":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X.json","graph_json":"https://pith.science/api/pith-number/GKQNBDK55JPUUBGJCH7YG32B2X/graph.json","events_json":"https://pith.science/api/pith-number/GKQNBDK55JPUUBGJCH7YG32B2X/events.json","paper":"https://pith.science/paper/GKQNBDK5"},"agent_actions":{"view_html":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X","download_json":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X.json","view_paper":"https://pith.science/paper/GKQNBDK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17551&json=true","fetch_graph":"https://pith.science/api/pith-number/GKQNBDK55JPUUBGJCH7YG32B2X/graph.json","fetch_events":"https://pith.science/api/pith-number/GKQNBDK55JPUUBGJCH7YG32B2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/action/storage_attestation","attest_author":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/action/author_attestation","sign_citation":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/action/citation_signature","submit_replication":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/action/replication_record"}},"created_at":"2026-06-01T01:03:53.315209+00:00","updated_at":"2026-06-01T01:03:53.315209+00:00"}