{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UHSSIVTSDCZQA5P53PDRHKCOKD","short_pith_number":"pith:UHSSIVTS","canonical_record":{"source":{"id":"1812.07626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:01:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8b16ecf3597c7a6fa48ddddbd10fd1ac3beae9007d13825ab54cdab086285c1f","abstract_canon_sha256":"85be2f7c39898ab0d5624ceaeaf3a1b3f02afe3bcf6055ea4197f032bc8cbe64"},"schema_version":"1.0"},"canonical_sha256":"a1e524567218b30075fddbc713a84e50fdeb8042c472a4a39dae9442cc5090a5","source":{"kind":"arxiv","id":"1812.07626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07626","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07626v1","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07626","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"UHSSIVTSDCZQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UHSSIVTSDCZQA5P5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UHSSIVTS","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UHSSIVTSDCZQA5P53PDRHKCOKD","target":"record","payload":{"canonical_record":{"source":{"id":"1812.07626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:01:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8b16ecf3597c7a6fa48ddddbd10fd1ac3beae9007d13825ab54cdab086285c1f","abstract_canon_sha256":"85be2f7c39898ab0d5624ceaeaf3a1b3f02afe3bcf6055ea4197f032bc8cbe64"},"schema_version":"1.0"},"canonical_sha256":"a1e524567218b30075fddbc713a84e50fdeb8042c472a4a39dae9442cc5090a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.515516Z","signature_b64":"BoMo5+0Kh0ZoSIWUeko+GKXn3DgP9PWSSLdWa4XahFHiTK5t8cOMOXPnGX/I22Dj9N0oHmcAyl8rsuMa2BWNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e524567218b30075fddbc713a84e50fdeb8042c472a4a39dae9442cc5090a5","last_reissued_at":"2026-05-17T23:57:56.514939Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.514939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.07626","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZxh4OXAYM5HBMwKRT2x8denLK5k9jUSt9VD2irZml5EEpc9ImB+pwm2ItpHFC0S5oKx7Q+qLcxYty9SlfJeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:11:55.949020Z"},"content_sha256":"10eccbeb0eb63afb6f80308cd8d17b259f58c19320d1f5232046122cfa105295","schema_version":"1.0","event_id":"sha256:10eccbeb0eb63afb6f80308cd8d17b259f58c19320d1f5232046122cfa105295"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UHSSIVTSDCZQA5P53PDRHKCOKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Successor Features Approximators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Daniel Mankowitz, David Silver, Diana Borsa, Hado van Hasselt, John Quan, R\\'emi Munos, Tom Schaul","submitted_at":"2018-12-18T20:01:41Z","abstract_excerpt":"The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability to generalise to unseen tasks. Parametric generalisation relies on the interpolation power of a function approximator that is given the task description as input; one of its most common form are universal value function approximators (UVFAs). Another way to generalise to new tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07626","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":""},"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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxSE5TSUUhTE+e78G8miNtUPBVuG7NViVSzErYJci5GrgxRSkIApZ1qlzh6nmC87epAYtq1s9GcelNKTCbBpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:11:55.949377Z"},"content_sha256":"a6ed8942e1aefaca3aff844ccc1ec514999215f86c073eac7d64ffcc3f97e195","schema_version":"1.0","event_id":"sha256:a6ed8942e1aefaca3aff844ccc1ec514999215f86c073eac7d64ffcc3f97e195"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/bundle.json","state_url":"https://pith.science/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/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":"2026-05-21T20:11:55Z","links":{"resolver":"https://pith.science/pith/UHSSIVTSDCZQA5P53PDRHKCOKD","bundle":"https://pith.science/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/bundle.json","state":"https://pith.science/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHSSIVTSDCZQA5P53PDRHKCOKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UHSSIVTSDCZQA5P53PDRHKCOKD","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":"85be2f7c39898ab0d5624ceaeaf3a1b3f02afe3bcf6055ea4197f032bc8cbe64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:01:41Z","title_canon_sha256":"8b16ecf3597c7a6fa48ddddbd10fd1ac3beae9007d13825ab54cdab086285c1f"},"schema_version":"1.0","source":{"id":"1812.07626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07626","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07626v1","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07626","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"UHSSIVTSDCZQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UHSSIVTSDCZQA5P5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UHSSIVTS","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:a6ed8942e1aefaca3aff844ccc1ec514999215f86c073eac7d64ffcc3f97e195","target":"graph","created_at":"2026-05-17T23:57:56Z","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":"The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability to generalise to unseen tasks. Parametric generalisation relies on the interpolation power of a function approximator that is given the task description as input; one of its most common form are universal value function approximators (UVFAs). Another way to generalise to new tas","authors_text":"Andr\\'e Barreto, Daniel Mankowitz, David Silver, Diana Borsa, Hado van Hasselt, John Quan, R\\'emi Munos, Tom Schaul","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:01:41Z","title":"Universal Successor Features Approximators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07626","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":"sha256:10eccbeb0eb63afb6f80308cd8d17b259f58c19320d1f5232046122cfa105295","target":"record","created_at":"2026-05-17T23:57:56Z","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":"85be2f7c39898ab0d5624ceaeaf3a1b3f02afe3bcf6055ea4197f032bc8cbe64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:01:41Z","title_canon_sha256":"8b16ecf3597c7a6fa48ddddbd10fd1ac3beae9007d13825ab54cdab086285c1f"},"schema_version":"1.0","source":{"id":"1812.07626","kind":"arxiv","version":1}},"canonical_sha256":"a1e524567218b30075fddbc713a84e50fdeb8042c472a4a39dae9442cc5090a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1e524567218b30075fddbc713a84e50fdeb8042c472a4a39dae9442cc5090a5","first_computed_at":"2026-05-17T23:57:56.514939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:56.514939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BoMo5+0Kh0ZoSIWUeko+GKXn3DgP9PWSSLdWa4XahFHiTK5t8cOMOXPnGX/I22Dj9N0oHmcAyl8rsuMa2BWNDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:56.515516Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10eccbeb0eb63afb6f80308cd8d17b259f58c19320d1f5232046122cfa105295","sha256:a6ed8942e1aefaca3aff844ccc1ec514999215f86c073eac7d64ffcc3f97e195"],"state_sha256":"02db46758be8d854c9c3fbac81b901f409c9deeb8e3ca62d1942292c77b2bc97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A5cpyW5S1K+093RgVhrg8CM2KnBEME9ccpua7Nn3mwZ71bevrKpWK/lwbKdXccScu3X8ETX8S83RO4l0RiWsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T20:11:55.951506Z","bundle_sha256":"1eb4e02393109f3be3aff4df224e2578bd81fc644a1ed1a5e93516feb7351635"}}