{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YDNCYSZEWHLLSNVSI3IPXGBJQP","short_pith_number":"pith:YDNCYSZE","canonical_record":{"source":{"id":"2507.18809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T21:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"ea51ed3063d1bf0826633598e375d49a5aff20700692c044e33f8ca422c8fb6a","abstract_canon_sha256":"31b05c4e4ad2ad4ef6c868fd12e1f1d3006b033a614144ba34d0928581d3f942"},"schema_version":"1.0"},"canonical_sha256":"c0da2c4b24b1d6b936b246d0fb982983f60cbbb21c8b0110cc64b437dd0c5c04","source":{"kind":"arxiv","id":"2507.18809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18809","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18809v2","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18809","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"YDNCYSZEWHLL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YDNCYSZEWHLLSNVS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YDNCYSZE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YDNCYSZEWHLLSNVSI3IPXGBJQP","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T21:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"ea51ed3063d1bf0826633598e375d49a5aff20700692c044e33f8ca422c8fb6a","abstract_canon_sha256":"31b05c4e4ad2ad4ef6c868fd12e1f1d3006b033a614144ba34d0928581d3f942"},"schema_version":"1.0"},"canonical_sha256":"c0da2c4b24b1d6b936b246d0fb982983f60cbbb21c8b0110cc64b437dd0c5c04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:34.981693Z","signature_b64":"mbrdAEjyLg5H387v14IpPYMiN5ysFJZ9mMAA8xExGkNWfH7vqrm5pOTiEJnx7iS6k96tE2D5LmN3fOO8JnljBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0da2c4b24b1d6b936b246d0fb982983f60cbbb21c8b0110cc64b437dd0c5c04","last_reissued_at":"2026-05-18T03:09:34.981253Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:34.981253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18809","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":"2026-05-18T03:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2D814yuSh1cLkdErPj6k2xUbJrn65c2VjUBL1NWRFuiYdOEuN8ln7OM3N1dPJ4JvgW7NmfkLI2Zmr1X5dYcNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:28:52.577939Z"},"content_sha256":"6840ddcae05dfc7d27856f7def8c63f2dd7c291fea347d355c840409aa85837f","schema_version":"1.0","event_id":"sha256:6840ddcae05dfc7d27856f7def8c63f2dd7c291fea347d355c840409aa85837f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YDNCYSZEWHLLSNVSI3IPXGBJQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-time Offline Reinforcement Learning on Goal-related Experience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Georg Martius, Jonas H\\\"ubotter, Marco Bagatella, Mert Albaba","submitted_at":"2025-07-24T21:11:39Z","abstract_excerpt":"Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18809","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGmz7sdTVyjlk0DP0JatzGXnF5TA7jQb2rhia6sh8frOGhvWns/AQfpsTF2bCJ3s3UD2lEC3c1NmA1RS5MQVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:28:52.578539Z"},"content_sha256":"6cb353c33dba458063cf40c89f2c21cd58bff4e478beeef9d64ea89132125569","schema_version":"1.0","event_id":"sha256:6cb353c33dba458063cf40c89f2c21cd58bff4e478beeef9d64ea89132125569"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/bundle.json","state_url":"https://pith.science/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/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":"2026-05-27T00:28:52Z","links":{"resolver":"https://pith.science/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP","bundle":"https://pith.science/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/bundle.json","state":"https://pith.science/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDNCYSZEWHLLSNVSI3IPXGBJQP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YDNCYSZEWHLLSNVSI3IPXGBJQP","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":"31b05c4e4ad2ad4ef6c868fd12e1f1d3006b033a614144ba34d0928581d3f942","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T21:11:39Z","title_canon_sha256":"ea51ed3063d1bf0826633598e375d49a5aff20700692c044e33f8ca422c8fb6a"},"schema_version":"1.0","source":{"id":"2507.18809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18809","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18809v2","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18809","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"YDNCYSZEWHLL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YDNCYSZEWHLLSNVS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YDNCYSZE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6cb353c33dba458063cf40c89f2c21cd58bff4e478beeef9d64ea89132125569","target":"graph","created_at":"2026-05-18T03:09:34Z","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"},"paper":{"abstract_excerpt":"Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time ","authors_text":"Andreas Krause, Georg Martius, Jonas H\\\"ubotter, Marco Bagatella, Mert Albaba","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T21:11:39Z","title":"Test-time Offline Reinforcement Learning on Goal-related Experience"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18809","kind":"arxiv","version":2},"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":"sha256:6840ddcae05dfc7d27856f7def8c63f2dd7c291fea347d355c840409aa85837f","target":"record","created_at":"2026-05-18T03:09:34Z","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":"31b05c4e4ad2ad4ef6c868fd12e1f1d3006b033a614144ba34d0928581d3f942","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T21:11:39Z","title_canon_sha256":"ea51ed3063d1bf0826633598e375d49a5aff20700692c044e33f8ca422c8fb6a"},"schema_version":"1.0","source":{"id":"2507.18809","kind":"arxiv","version":2}},"canonical_sha256":"c0da2c4b24b1d6b936b246d0fb982983f60cbbb21c8b0110cc64b437dd0c5c04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0da2c4b24b1d6b936b246d0fb982983f60cbbb21c8b0110cc64b437dd0c5c04","first_computed_at":"2026-05-18T03:09:34.981253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:34.981253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mbrdAEjyLg5H387v14IpPYMiN5ysFJZ9mMAA8xExGkNWfH7vqrm5pOTiEJnx7iS6k96tE2D5LmN3fOO8JnljBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:34.981693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6840ddcae05dfc7d27856f7def8c63f2dd7c291fea347d355c840409aa85837f","sha256:6cb353c33dba458063cf40c89f2c21cd58bff4e478beeef9d64ea89132125569"],"state_sha256":"6fa45f707ee33fa814cee0c6ed2b148904d82c166fa1e3b7cf0d072a3ee7b12d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6CJ0nHTiIwBdNjMb6sNJ/cWLbcazGe5XQpBUnK9dTZv8c8+pOR7oXYv79hBL/v4cRlR6LtqlZ5NIWPJSNg9nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:28:52.581626Z","bundle_sha256":"daf04de6ea8b316255cbbdd9208eb8ed7a81221847d5c794b60f5a789ea482b1"}}