{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GKQNBDK55JPUUBGJCH7YG32B2X","short_pith_number":"pith:GKQNBDK5","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"},"canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","source":{"kind":"arxiv","id":"2604.17551","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17551","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17551v2","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17551","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"GKQNBDK55JPU","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"GKQNBDK55JPUUBGJ","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"GKQNBDK5","created_at":"2026-06-01T01:03:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GKQNBDK55JPUUBGJCH7YG32B2X","target":"record","payload":{"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"},"canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","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"},"source_kind":"arxiv","source_id":"2604.17551","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SE/6q4oYVkxaoPuPsRJYWs5JOeLA0SG/Fnl9WtgL80ux5gDSqPXeltTgoUDBdMKKp1s/55qHqXvfx1RjKuHkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:26:01.013193Z"},"content_sha256":"07859bf2b7a330fee5c00460ddcb3e3fc6ca4f539889642dfb0bfe3645eff8d6","schema_version":"1.0","event_id":"sha256:07859bf2b7a330fee5c00460ddcb3e3fc6ca4f539889642dfb0bfe3645eff8d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GKQNBDK55JPUUBGJCH7YG32B2X","target":"graph","payload":{"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"},"verdict_id":"369fb219-d8d7-47ec-8b27-61441b58355b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXBX5HRb3TBR/wiURarNfDTnGLKzoTYlQhCNFUVKx9u/OvaMbhq3187YnPuUUddMMTLx+61X+eYvCzNKdEGQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:26:01.013852Z"},"content_sha256":"78d88d6963b6e36a61854e30a841f965387891d8bf975f956be345c3be4e7a64","schema_version":"1.0","event_id":"sha256:78d88d6963b6e36a61854e30a841f965387891d8bf975f956be345c3be4e7a64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/bundle.json","state_url":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKQNBDK55JPUUBGJCH7YG32B2X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T00:26:01Z","links":{"resolver":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X","bundle":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/bundle.json","state":"https://pith.science/pith/GKQNBDK55JPUUBGJCH7YG32B2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKQNBDK55JPUUBGJCH7YG32B2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GKQNBDK55JPUUBGJCH7YG32B2X","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":"323de9196b25189805225d400185f8b287b6edc59cc055c7230178f9eca48999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T17:44:13Z","title_canon_sha256":"6f04d9c29ff742410496f820d3317476e16e695943603766e5c0b1f5f7a2caf1"},"schema_version":"1.0","source":{"id":"2604.17551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17551","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17551v2","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17551","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"GKQNBDK55JPU","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"GKQNBDK55JPUUBGJ","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"GKQNBDK5","created_at":"2026-06-01T01:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:78d88d6963b6e36a61854e30a841f965387891d8bf975f956be345c3be4e7a64","target":"graph","created_at":"2026-06-01T01:03:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The goal-conditioned value function equals a discounted sum of survival probabilities over time."}],"snapshot_sha256":"dda31e33a9c284b4b49ad1db146bed5e837c368ecaf7f8737bada6382368ed50"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fabian Schramm, Franki Nguimatsia Tiofack, Justin Carpentier, Th\\'eotime Le Hellard","cross_cats":["cs.AI"],"headline":"The goal-conditioned value function equals a discounted sum of survival probabilities over time.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T17:44:13Z","title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17551","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T06:41:08.833872Z","id":"369fb219-d8d7-47ec-8b27-61441b58355b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"The goal-conditioned value function equals a discounted sum of survival probabilities over time.","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.","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."}},"verdict_id":"369fb219-d8d7-47ec-8b27-61441b58355b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:07859bf2b7a330fee5c00460ddcb3e3fc6ca4f539889642dfb0bfe3645eff8d6","target":"record","created_at":"2026-06-01T01:03:53Z","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":"323de9196b25189805225d400185f8b287b6edc59cc055c7230178f9eca48999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T17:44:13Z","title_canon_sha256":"6f04d9c29ff742410496f820d3317476e16e695943603766e5c0b1f5f7a2caf1"},"schema_version":"1.0","source":{"id":"2604.17551","kind":"arxiv","version":2}},"canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32a0d08d5dea5f4a04c911ff836f41d5c32fd0a87875e527a0a224d22f7f3dd4","first_computed_at":"2026-06-01T01:03:53.315040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:53.315040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1pV1AGqF+uFJrrXr7hhwa9jYM+MaP52fUpNrm962fNdzJEYkF3q5SSEFi4sjndc7I5tvWXJdhR/g7jegUd70Ag==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:53.316224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07859bf2b7a330fee5c00460ddcb3e3fc6ca4f539889642dfb0bfe3645eff8d6","sha256:78d88d6963b6e36a61854e30a841f965387891d8bf975f956be345c3be4e7a64"],"state_sha256":"195a9c72f440aed7558e9ef5c576c502ccc1ddaff057030efe242df9c0920005"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NblJPRWZXJR6aPBoBx2cSK8Nqwak2k8hJcFHUlRc+QJb2q7VUZ9YRhbRymFEkmNCd3s7mWzCKwud3S/bPIIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:26:01.021223Z","bundle_sha256":"a7c54a7c447a54fa1b824bbf006c8575a24b27dfb0a6bd1e9fa364dc4bf15efb"}}