{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZEP54EVZIA27KSNKWBAEMOWZPC","short_pith_number":"pith:ZEP54EVZ","canonical_record":{"source":{"id":"2605.23551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:17:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"689e5681a3264009f672fe9e60218435572aa11a69248bc80d83fbb71bbe650e","abstract_canon_sha256":"e1344715d29d2aca66bf1e74214087e58e06d86854bd59e6ae40c5196427d205"},"schema_version":"1.0"},"canonical_sha256":"c91fde12b94035f549aab040463ad978b88ba91a2e7c2565c6b63d392288a4dd","source":{"kind":"arxiv","id":"2605.23551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23551","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23551v1","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23551","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZEP54EVZIA27","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZEP54EVZIA27KSNK","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZEP54EVZ","created_at":"2026-05-25T02:02:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZEP54EVZIA27KSNKWBAEMOWZPC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:17:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"689e5681a3264009f672fe9e60218435572aa11a69248bc80d83fbb71bbe650e","abstract_canon_sha256":"e1344715d29d2aca66bf1e74214087e58e06d86854bd59e6ae40c5196427d205"},"schema_version":"1.0"},"canonical_sha256":"c91fde12b94035f549aab040463ad978b88ba91a2e7c2565c6b63d392288a4dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:00.544766Z","signature_b64":"Tt/d145Z6T850VZz1BQpSKaMveh5nhILTOuaG/zuaPa1kOFemgSOVZIzMp59AaDxx6opIQx4NknX0FLLrmckAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c91fde12b94035f549aab040463ad978b88ba91a2e7c2565c6b63d392288a4dd","last_reissued_at":"2026-05-25T02:02:00.543924Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:00.543924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23551","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qtG5pXujfuMHhJShm+dKwOi7CeebSTBA8bhfiWkSPSQfcJJhqFE1SiYaExwL25ke4K1QV9WCDYCFycdfP54Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:42.419443Z"},"content_sha256":"f251f9d3aa6febd3bbe81b011b067deee47d68798e330001f0d16c93792e4286","schema_version":"1.0","event_id":"sha256:f251f9d3aa6febd3bbe81b011b067deee47d68798e330001f0d16c93792e4286"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZEP54EVZIA27KSNKWBAEMOWZPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-Conditioned Agents that Learn Everything All at Once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alistair Letcher, C\\'edric Colas, Jakob Foerster, Matthew Jackson, Michael Beukman, Michael Matthews, Scott Fujimoto, Thomas Foster","submitted_at":"2026-05-22T12:17:09Z","abstract_excerpt":"A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal. All-goals learning, where each transition is used for learning off-policy with respect to every goal, allows agents to extract maximal information, however it is usually computationally infeasible when done via naive relabelling. This can be overcome by jointly outputting values and actions for every goal at once, allowing for efficient, parallel all-goals updates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23551","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/2605.23551/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FooL9oIDIa/v1SsR2fbbX7TS4SawpEgZM6INZFXO84lYtVoaMWlk8xk/NoP49L5X2May/7iU8v6O3tPslNSqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:42.420024Z"},"content_sha256":"b316edcb25d81b514131b1a2d9e57c0c2c13bd72b712b9d8cb64fab614a9acb1","schema_version":"1.0","event_id":"sha256:b316edcb25d81b514131b1a2d9e57c0c2c13bd72b712b9d8cb64fab614a9acb1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/bundle.json","state_url":"https://pith.science/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/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":"2026-05-25T17:11:42Z","links":{"resolver":"https://pith.science/pith/ZEP54EVZIA27KSNKWBAEMOWZPC","bundle":"https://pith.science/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/bundle.json","state":"https://pith.science/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEP54EVZIA27KSNKWBAEMOWZPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEP54EVZIA27KSNKWBAEMOWZPC","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":"e1344715d29d2aca66bf1e74214087e58e06d86854bd59e6ae40c5196427d205","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:17:09Z","title_canon_sha256":"689e5681a3264009f672fe9e60218435572aa11a69248bc80d83fbb71bbe650e"},"schema_version":"1.0","source":{"id":"2605.23551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23551","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23551v1","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23551","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZEP54EVZIA27","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZEP54EVZIA27KSNK","created_at":"2026-05-25T02:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZEP54EVZ","created_at":"2026-05-25T02:02:00Z"}],"graph_snapshots":[{"event_id":"sha256:b316edcb25d81b514131b1a2d9e57c0c2c13bd72b712b9d8cb64fab614a9acb1","target":"graph","created_at":"2026-05-25T02:02:00Z","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/2605.23551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal. All-goals learning, where each transition is used for learning off-policy with respect to every goal, allows agents to extract maximal information, however it is usually computationally infeasible when done via naive relabelling. This can be overcome by jointly outputting values and actions for every goal at once, allowing for efficient, parallel all-goals updates ","authors_text":"Alistair Letcher, C\\'edric Colas, Jakob Foerster, Matthew Jackson, Michael Beukman, Michael Matthews, Scott Fujimoto, Thomas Foster","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:17:09Z","title":"Goal-Conditioned Agents that Learn Everything All at Once"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23551","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:f251f9d3aa6febd3bbe81b011b067deee47d68798e330001f0d16c93792e4286","target":"record","created_at":"2026-05-25T02:02:00Z","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":"e1344715d29d2aca66bf1e74214087e58e06d86854bd59e6ae40c5196427d205","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:17:09Z","title_canon_sha256":"689e5681a3264009f672fe9e60218435572aa11a69248bc80d83fbb71bbe650e"},"schema_version":"1.0","source":{"id":"2605.23551","kind":"arxiv","version":1}},"canonical_sha256":"c91fde12b94035f549aab040463ad978b88ba91a2e7c2565c6b63d392288a4dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c91fde12b94035f549aab040463ad978b88ba91a2e7c2565c6b63d392288a4dd","first_computed_at":"2026-05-25T02:02:00.543924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:00.543924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tt/d145Z6T850VZz1BQpSKaMveh5nhILTOuaG/zuaPa1kOFemgSOVZIzMp59AaDxx6opIQx4NknX0FLLrmckAg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:00.544766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f251f9d3aa6febd3bbe81b011b067deee47d68798e330001f0d16c93792e4286","sha256:b316edcb25d81b514131b1a2d9e57c0c2c13bd72b712b9d8cb64fab614a9acb1"],"state_sha256":"b0900c01464eca9066a1b13026e87ffdb543a4b789c6aa3f68a8d2a9798ffefb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZE3wXLNxGIrERKcjK1lnZ5DoqVScmMNGaUTpnoSKHj9xt0eqMc/eiE2F4GlmUrGoIIxZ3QLbNd0Qj+YP8G9HCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:11:42.424051Z","bundle_sha256":"1d5b4d763e1486b5baafbd10d9c9c27342eddbb4eaa407678c73d4163400ae05"}}