{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:E7XJ67OE5GAYNATNWS3W3SNMHJ","short_pith_number":"pith:E7XJ67OE","canonical_record":{"source":{"id":"2011.07318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T15:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eacdf83f38b1617f88a744bca54a2c53420ae8b58238feadb6ba755fe3bab11a","abstract_canon_sha256":"92ddb48b83944728fe1958ddde9ff1d3a1fb287a2ca28ca8a7138da4172b5080"},"schema_version":"1.0"},"canonical_sha256":"27ee9f7dc4e98186826db4b76dc9ac3a715e482d18d14938dfce20920b91ef90","source":{"kind":"arxiv","id":"2011.07318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07318","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07318v1","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07318","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"E7XJ67OE5GAY","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"E7XJ67OE5GAYNATN","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"E7XJ67OE","created_at":"2026-07-05T01:51:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:E7XJ67OE5GAYNATNWS3W3SNMHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2011.07318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T15:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eacdf83f38b1617f88a744bca54a2c53420ae8b58238feadb6ba755fe3bab11a","abstract_canon_sha256":"92ddb48b83944728fe1958ddde9ff1d3a1fb287a2ca28ca8a7138da4172b5080"},"schema_version":"1.0"},"canonical_sha256":"27ee9f7dc4e98186826db4b76dc9ac3a715e482d18d14938dfce20920b91ef90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:48.307057Z","signature_b64":"Yd9nVugYaydh7yUd/j9RR55N0Zle03p+MFTsJojFK4RV8+5p1P7lU6CNXg/RPMf0vZC0pXQKp5mhWpkqChVbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27ee9f7dc4e98186826db4b76dc9ac3a715e482d18d14938dfce20920b91ef90","last_reissued_at":"2026-07-05T01:51:48.306612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:48.306612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.07318","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":"2026-07-05T01:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yPYl02OJIWqwRme6Bn2FWHQC3Xi61GptGM1sFwtzsam04s+gftv8MnE9rgERvDDZjvVx3ZLAmliXykyYztvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:12.776666Z"},"content_sha256":"93cf5c6f38d92b7809b9073157ddd8151bc6b81b0fa75d6ce6ac9124bc82808c","schema_version":"1.0","event_id":"sha256:93cf5c6f38d92b7809b9073157ddd8151bc6b81b0fa75d6ce6ac9124bc82808c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:E7XJ67OE5GAYNATNWS3W3SNMHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Geometric Perspective on Self-Supervised Policy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cristian Bodnar, Gabriel Dulac-Arnold, Karol Hausman, Rico Jonschkowski","submitted_at":"2020-11-14T15:16:43Z","abstract_excerpt":"One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment. While an agent could learn from reward signals to ignore them, the complexity of the real-world can make rewards hard to acquire, or, at best, extremely sparse. A recent class of self-supervised methods have shown promise that reward-free adaptation under challenging distractions is possible. However, previous work focused on a short one-episode adaptation setting. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07318","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/2011.07318/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":"2026-07-05T01:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ut/pLLQiyh1AycFu57JCCPJZRiiFknetq9zMWQoJkxEbniFNpgfYBrNYSxf4PIB3d37wGQGcNYRu2iYWzqYVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:12.777064Z"},"content_sha256":"27d801edcae2a12a96a0b9c6806c04afdf527fa7d023705451ea4e9b8ea0c36e","schema_version":"1.0","event_id":"sha256:27d801edcae2a12a96a0b9c6806c04afdf527fa7d023705451ea4e9b8ea0c36e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/bundle.json","state_url":"https://pith.science/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/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":"2026-07-07T13:44:12Z","links":{"resolver":"https://pith.science/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ","bundle":"https://pith.science/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/bundle.json","state":"https://pith.science/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7XJ67OE5GAYNATNWS3W3SNMHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:E7XJ67OE5GAYNATNWS3W3SNMHJ","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":"92ddb48b83944728fe1958ddde9ff1d3a1fb287a2ca28ca8a7138da4172b5080","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T15:16:43Z","title_canon_sha256":"eacdf83f38b1617f88a744bca54a2c53420ae8b58238feadb6ba755fe3bab11a"},"schema_version":"1.0","source":{"id":"2011.07318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07318","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07318v1","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07318","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"E7XJ67OE5GAY","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"E7XJ67OE5GAYNATN","created_at":"2026-07-05T01:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"E7XJ67OE","created_at":"2026-07-05T01:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:27d801edcae2a12a96a0b9c6806c04afdf527fa7d023705451ea4e9b8ea0c36e","target":"graph","created_at":"2026-07-05T01:51:48Z","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/2011.07318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment. While an agent could learn from reward signals to ignore them, the complexity of the real-world can make rewards hard to acquire, or, at best, extremely sparse. A recent class of self-supervised methods have shown promise that reward-free adaptation under challenging distractions is possible. However, previous work focused on a short one-episode adaptation setting. In thi","authors_text":"Cristian Bodnar, Gabriel Dulac-Arnold, Karol Hausman, Rico Jonschkowski","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T15:16:43Z","title":"A Geometric Perspective on Self-Supervised Policy Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07318","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":"sha256:93cf5c6f38d92b7809b9073157ddd8151bc6b81b0fa75d6ce6ac9124bc82808c","target":"record","created_at":"2026-07-05T01:51:48Z","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":"92ddb48b83944728fe1958ddde9ff1d3a1fb287a2ca28ca8a7138da4172b5080","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T15:16:43Z","title_canon_sha256":"eacdf83f38b1617f88a744bca54a2c53420ae8b58238feadb6ba755fe3bab11a"},"schema_version":"1.0","source":{"id":"2011.07318","kind":"arxiv","version":1}},"canonical_sha256":"27ee9f7dc4e98186826db4b76dc9ac3a715e482d18d14938dfce20920b91ef90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27ee9f7dc4e98186826db4b76dc9ac3a715e482d18d14938dfce20920b91ef90","first_computed_at":"2026-07-05T01:51:48.306612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:48.306612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yd9nVugYaydh7yUd/j9RR55N0Zle03p+MFTsJojFK4RV8+5p1P7lU6CNXg/RPMf0vZC0pXQKp5mhWpkqChVbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:48.307057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.07318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93cf5c6f38d92b7809b9073157ddd8151bc6b81b0fa75d6ce6ac9124bc82808c","sha256:27d801edcae2a12a96a0b9c6806c04afdf527fa7d023705451ea4e9b8ea0c36e"],"state_sha256":"1414acdd025d10aad3e24ec8513957057f54a99ffaf66da7b05e6c06227b6481"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNFqUsWZUGvUP8QZRIWE37D95rTAcmyyOem1a9W25/5s6NvRX6TgVRuFOuZvhqUIVnUTRWOMaEBbN0RFinHfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:44:12.779019Z","bundle_sha256":"b1279ed2127a3046463129e047eb20018cf296e39650b481f206725e7f1efa61"}}