{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4LIEYQBA5RMOPV2HAS2MIVVNW4","short_pith_number":"pith:4LIEYQBA","canonical_record":{"source":{"id":"2010.14484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"c898972433f19c1f60deedb160059d6f8293c3801ae7b98b5a83e0046a4cf79a","abstract_canon_sha256":"27e26905c840c85a028246edb7f1244ec18e28731207b6f7e496998086211139"},"schema_version":"1.0"},"canonical_sha256":"e2d04c4020ec58e7d74704b4c456adb70ab6331e6987fc70a411b888a7a8de1b","source":{"kind":"arxiv","id":"2010.14484","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14484","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14484v2","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14484","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"4LIEYQBA5RMO","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"4LIEYQBA5RMOPV2H","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"4LIEYQBA","created_at":"2026-07-05T01:57:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4LIEYQBA5RMOPV2HAS2MIVVNW4","target":"record","payload":{"canonical_record":{"source":{"id":"2010.14484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"c898972433f19c1f60deedb160059d6f8293c3801ae7b98b5a83e0046a4cf79a","abstract_canon_sha256":"27e26905c840c85a028246edb7f1244ec18e28731207b6f7e496998086211139"},"schema_version":"1.0"},"canonical_sha256":"e2d04c4020ec58e7d74704b4c456adb70ab6331e6987fc70a411b888a7a8de1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:36.504611Z","signature_b64":"fkKRlcheK+NozO4z+L0RlQsysJndPneTDvGVPeGEGXMNf6FgRY0doPiW/MubSp03MVpm8Y3TlowH3N0v76kwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2d04c4020ec58e7d74704b4c456adb70ab6331e6987fc70a411b888a7a8de1b","last_reissued_at":"2026-07-05T01:57:36.504146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:36.504146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.14484","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":"2026-07-05T01:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3IMxobusoB6kJ2niZBgasHQKoIboW4MbQCPNFgSevVmToR509JdmKB//NscPUUTsw8L1JEUcTTp+ory3ae9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:53:47.447350Z"},"content_sha256":"03af361508b08394705cc80781cebb2c846521de863d038ef134d3b0ddfe8751","schema_version":"1.0","event_id":"sha256:03af361508b08394705cc80781cebb2c846521de863d038ef134d3b0ddfe8751"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4LIEYQBA5RMOPV2HAS2MIVVNW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviral Kumar, Chelsea Finn, Saurabh Kumar, Sergey Levine","submitted_at":"2020-10-27T17:41:57Z","abstract_excerpt":"While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specified variation in the training task or environment. However, this may be infeasible in practical situations, either because making perturbations is not possible, or because it is unclear how to choose suitable perturbation strategies without sacrificing performance. The key insight of this work is th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14484","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.14484/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":"2026-07-05T01:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3IBy5ac6GagLMPWhVv16lNFThDUvPvmabmITM+qs6i1NgWXAS7oETIbDuGAD0rzTUjWce+xtauJsXyzlbaeZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:53:47.447826Z"},"content_sha256":"0d7d84afec062e2a3fa9c8f5f795c8128dab9b4e4db10e62f1240ca29df5c6c8","schema_version":"1.0","event_id":"sha256:0d7d84afec062e2a3fa9c8f5f795c8128dab9b4e4db10e62f1240ca29df5c6c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/bundle.json","state_url":"https://pith.science/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/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":"2026-08-05T23:53:47Z","links":{"resolver":"https://pith.science/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4","bundle":"https://pith.science/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/bundle.json","state":"https://pith.science/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4LIEYQBA5RMOPV2HAS2MIVVNW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4LIEYQBA5RMOPV2HAS2MIVVNW4","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":"27e26905c840c85a028246edb7f1244ec18e28731207b6f7e496998086211139","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:41:57Z","title_canon_sha256":"c898972433f19c1f60deedb160059d6f8293c3801ae7b98b5a83e0046a4cf79a"},"schema_version":"1.0","source":{"id":"2010.14484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14484","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14484v2","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14484","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"4LIEYQBA5RMO","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"4LIEYQBA5RMOPV2H","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"4LIEYQBA","created_at":"2026-07-05T01:57:36Z"}],"graph_snapshots":[{"event_id":"sha256:0d7d84afec062e2a3fa9c8f5f795c8128dab9b4e4db10e62f1240ca29df5c6c8","target":"graph","created_at":"2026-07-05T01:57:36Z","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/2010.14484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specified variation in the training task or environment. However, this may be infeasible in practical situations, either because making perturbations is not possible, or because it is unclear how to choose suitable perturbation strategies without sacrificing performance. The key insight of this work is th","authors_text":"Aviral Kumar, Chelsea Finn, Saurabh Kumar, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:41:57Z","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14484","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":"sha256:03af361508b08394705cc80781cebb2c846521de863d038ef134d3b0ddfe8751","target":"record","created_at":"2026-07-05T01:57:36Z","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":"27e26905c840c85a028246edb7f1244ec18e28731207b6f7e496998086211139","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:41:57Z","title_canon_sha256":"c898972433f19c1f60deedb160059d6f8293c3801ae7b98b5a83e0046a4cf79a"},"schema_version":"1.0","source":{"id":"2010.14484","kind":"arxiv","version":2}},"canonical_sha256":"e2d04c4020ec58e7d74704b4c456adb70ab6331e6987fc70a411b888a7a8de1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2d04c4020ec58e7d74704b4c456adb70ab6331e6987fc70a411b888a7a8de1b","first_computed_at":"2026-07-05T01:57:36.504146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:36.504146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fkKRlcheK+NozO4z+L0RlQsysJndPneTDvGVPeGEGXMNf6FgRY0doPiW/MubSp03MVpm8Y3TlowH3N0v76kwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:36.504611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03af361508b08394705cc80781cebb2c846521de863d038ef134d3b0ddfe8751","sha256:0d7d84afec062e2a3fa9c8f5f795c8128dab9b4e4db10e62f1240ca29df5c6c8"],"state_sha256":"94a2d8af07b373928b994195b7477c6652b32012d1838df3390611a87276be51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UGjxSlmVeLMyqqp6rSHIof2AWBRVCHKv2bideUb2tAZzHvpSeIaDV0dkGbAuRaGzmd+EW+GlNN9XboVdm3MCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:53:47.451658Z","bundle_sha256":"787f4210ec19183dbd6d747d560047f04201730b3bea08f19c54c78ed6fbe93c"}}