{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GYIVOERJSFD6XIZMMHWAXVXNUH","short_pith_number":"pith:GYIVOERJ","canonical_record":{"source":{"id":"2007.04309","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T17:56:27Z","cross_cats_sorted":["cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"d91c359abf2e2166093c033b9680981094735fa9cd4e90cfeee063e132d2ee93","abstract_canon_sha256":"8b17931a697d96f76cf592710b203e7d06c09692fa6028165901d5684b9f90bf"},"schema_version":"1.0"},"canonical_sha256":"36115712299147eba32c61ec0bd6eda1feda70ad1f124fb3e47dee4553c81a32","source":{"kind":"arxiv","id":"2007.04309","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04309","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04309v3","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04309","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"GYIVOERJSFD6","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"GYIVOERJSFD6XIZM","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"GYIVOERJ","created_at":"2026-07-05T02:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GYIVOERJSFD6XIZMMHWAXVXNUH","target":"record","payload":{"canonical_record":{"source":{"id":"2007.04309","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T17:56:27Z","cross_cats_sorted":["cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"d91c359abf2e2166093c033b9680981094735fa9cd4e90cfeee063e132d2ee93","abstract_canon_sha256":"8b17931a697d96f76cf592710b203e7d06c09692fa6028165901d5684b9f90bf"},"schema_version":"1.0"},"canonical_sha256":"36115712299147eba32c61ec0bd6eda1feda70ad1f124fb3e47dee4553c81a32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:29.110870Z","signature_b64":"RsvO9KQtfI+4pDvogMQkH8kBbONktCsXSxSpq/hp5L2N1CzC9c0uagFh1OpKcM/6O0rfDIWQUL31wFkhmJD9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36115712299147eba32c61ec0bd6eda1feda70ad1f124fb3e47dee4553c81a32","last_reissued_at":"2026-07-05T02:30:29.110370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:29.110370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.04309","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBe010OLvZ2woubmwH+/xU5MnDJkhmC7RdElfcS+Ea8BuxsMf8gyplov6oha720wi0DJP4xi157WODU6nbStDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:35:56.627764Z"},"content_sha256":"370dac3d83d9487cc721c5ec975393cc94589ada675145864e60560b6a8a0204","schema_version":"1.0","event_id":"sha256:370dac3d83d9487cc721c5ec975393cc94589ada675145864e60560b6a8a0204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GYIVOERJSFD6XIZMMHWAXVXNUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Policy Adaptation during Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Guillem Aleny\\`a, Lerrel Pinto, Nicklas Hansen, Pieter Abbeel, Rishabh Jangir, Xiaolong Wang, Yu Sun","submitted_at":"2020-07-08T17:56:27Z","abstract_excerpt":"In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new enviro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04309","kind":"arxiv","version":3},"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/2007.04309/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":"2026-07-05T02:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LOtwm3mnRfgyHot+pF5OVCD1yOk//lqj00VHEg8lOgxQtXr5R71X7dqglSdfTAuS76b6S+iISd1iL6J0oAP9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:35:56.628349Z"},"content_sha256":"462dfc560fe5933e2dd5753003daf90fb74e7dfc8594bb7f023fd87ad030e750","schema_version":"1.0","event_id":"sha256:462dfc560fe5933e2dd5753003daf90fb74e7dfc8594bb7f023fd87ad030e750"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/bundle.json","state_url":"https://pith.science/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/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":"2026-08-07T19:35:56Z","links":{"resolver":"https://pith.science/pith/GYIVOERJSFD6XIZMMHWAXVXNUH","bundle":"https://pith.science/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/bundle.json","state":"https://pith.science/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYIVOERJSFD6XIZMMHWAXVXNUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GYIVOERJSFD6XIZMMHWAXVXNUH","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":"8b17931a697d96f76cf592710b203e7d06c09692fa6028165901d5684b9f90bf","cross_cats_sorted":["cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T17:56:27Z","title_canon_sha256":"d91c359abf2e2166093c033b9680981094735fa9cd4e90cfeee063e132d2ee93"},"schema_version":"1.0","source":{"id":"2007.04309","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04309","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04309v3","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04309","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"GYIVOERJSFD6","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"GYIVOERJSFD6XIZM","created_at":"2026-07-05T02:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"GYIVOERJ","created_at":"2026-07-05T02:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:462dfc560fe5933e2dd5753003daf90fb74e7dfc8594bb7f023fd87ad030e750","target":"graph","created_at":"2026-07-05T02:30:29Z","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/2007.04309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new enviro","authors_text":"Alexei A. Efros, Guillem Aleny\\`a, Lerrel Pinto, Nicklas Hansen, Pieter Abbeel, Rishabh Jangir, Xiaolong Wang, Yu Sun","cross_cats":["cs.CV","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T17:56:27Z","title":"Self-Supervised Policy Adaptation during Deployment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04309","kind":"arxiv","version":3},"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":"sha256:370dac3d83d9487cc721c5ec975393cc94589ada675145864e60560b6a8a0204","target":"record","created_at":"2026-07-05T02:30:29Z","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":"8b17931a697d96f76cf592710b203e7d06c09692fa6028165901d5684b9f90bf","cross_cats_sorted":["cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T17:56:27Z","title_canon_sha256":"d91c359abf2e2166093c033b9680981094735fa9cd4e90cfeee063e132d2ee93"},"schema_version":"1.0","source":{"id":"2007.04309","kind":"arxiv","version":3}},"canonical_sha256":"36115712299147eba32c61ec0bd6eda1feda70ad1f124fb3e47dee4553c81a32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36115712299147eba32c61ec0bd6eda1feda70ad1f124fb3e47dee4553c81a32","first_computed_at":"2026-07-05T02:30:29.110370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:29.110370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RsvO9KQtfI+4pDvogMQkH8kBbONktCsXSxSpq/hp5L2N1CzC9c0uagFh1OpKcM/6O0rfDIWQUL31wFkhmJD9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:29.110870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.04309","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:370dac3d83d9487cc721c5ec975393cc94589ada675145864e60560b6a8a0204","sha256:462dfc560fe5933e2dd5753003daf90fb74e7dfc8594bb7f023fd87ad030e750"],"state_sha256":"e7dca28510f7c22df71d5ef10b2fcb9c63ac0d5c75b3599961a898c9de256fb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zlNzAgG1c9jcxb5MVjeeKVvjG2EzCjHmrZGdFVJ2C0IIxvAr49xogYCSUsej4Jbx7LiXuiZ67n5nyaKr5rDUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:35:56.632590Z","bundle_sha256":"aa029ae1840ce7b9d4936f05b4177c31a33f175108109747e8120b1d7f0c5faf"}}