{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FRRWBJQHL5KISVP3PC4M3PQOOF","short_pith_number":"pith:FRRWBJQH","canonical_record":{"source":{"id":"2106.04480","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T16:07:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6f04f6a536cd86bb4e4c144e3c9b0270bb5261094f6a7476e8fa9b5e8c1476b","abstract_canon_sha256":"34b28e99baf86f003aae99b68fe36c70dcad9adccf2ea06237379a14390fd6bf"},"schema_version":"1.0"},"canonical_sha256":"2c6360a6075f548955fb78b8cdbe0e715dd21113453e1fb92801eb5ec40be5c4","source":{"kind":"arxiv","id":"2106.04480","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04480","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04480v3","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04480","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"FRRWBJQHL5KI","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"FRRWBJQHL5KISVP3","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"FRRWBJQH","created_at":"2026-07-05T03:27:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FRRWBJQHL5KISVP3PC4M3PQOOF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.04480","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T16:07:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6f04f6a536cd86bb4e4c144e3c9b0270bb5261094f6a7476e8fa9b5e8c1476b","abstract_canon_sha256":"34b28e99baf86f003aae99b68fe36c70dcad9adccf2ea06237379a14390fd6bf"},"schema_version":"1.0"},"canonical_sha256":"2c6360a6075f548955fb78b8cdbe0e715dd21113453e1fb92801eb5ec40be5c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:03.169430Z","signature_b64":"FptBHsenrYDp12qUsLlSxZFoaDe6t05xbLrjwwO4vC1ArI0zRg/6P76wRi+eX7dhhItVaZAfS7HtBGzrkBCFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6360a6075f548955fb78b8cdbe0e715dd21113453e1fb92801eb5ec40be5c4","last_reissued_at":"2026-07-05T03:27:03.168947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:03.168947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.04480","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":"2026-07-05T03:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kZFae4jyKZttSEgblRCGnEFMcqs/mXbLpo6UQJKgHBMVvAGveiBC48U7qCR5vQOLZT7n+IqAb8fZNbA43yOpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:32:29.388965Z"},"content_sha256":"626053bc403db96f7c4f7fb5631d28306260021028a4fc76a6ea5781d8501a45","schema_version":"1.0","event_id":"sha256:626053bc403db96f7c4f7fb5631d28306260021028a4fc76a6ea5781d8501a45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FRRWBJQHL5KISVP3PC4M3PQOOF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johan Ferret, Matthieu Geist, Nathan Grinsztajn, Olivier Pietquin, Philippe Preux","submitted_at":"2021-06-08T16:07:10Z","abstract_excerpt":"We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show that approximate reversibility can be learned through a simple surrogate task: ranking randomly sampled trajectory events in chronological order. Intuitively, pairs of events that are always observed in the same order are likely to be separated by an irreversible sequence of actions. Conveniently, learning the temporal order of events can be done in a fully self-supervised way, which we use to estimate the reversibi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04480","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/2106.04480/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":"2026-07-05T03:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XYk0iSooV+MFTmYca7b31LxHfCD/f9heogzQt4+jWvLZ0bNahMsyypDcKML7DTBFqcQ1CPnODfSaSlM9V3zBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:32:29.389371Z"},"content_sha256":"a62d255677bf61549eca77b2ce571cc766d9f1e50a40925d675f97412e65bd1f","schema_version":"1.0","event_id":"sha256:a62d255677bf61549eca77b2ce571cc766d9f1e50a40925d675f97412e65bd1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/bundle.json","state_url":"https://pith.science/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/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":"2026-07-10T12:32:29Z","links":{"resolver":"https://pith.science/pith/FRRWBJQHL5KISVP3PC4M3PQOOF","bundle":"https://pith.science/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/bundle.json","state":"https://pith.science/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRRWBJQHL5KISVP3PC4M3PQOOF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FRRWBJQHL5KISVP3PC4M3PQOOF","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":"34b28e99baf86f003aae99b68fe36c70dcad9adccf2ea06237379a14390fd6bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T16:07:10Z","title_canon_sha256":"d6f04f6a536cd86bb4e4c144e3c9b0270bb5261094f6a7476e8fa9b5e8c1476b"},"schema_version":"1.0","source":{"id":"2106.04480","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04480","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04480v3","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04480","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"FRRWBJQHL5KI","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"FRRWBJQHL5KISVP3","created_at":"2026-07-05T03:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"FRRWBJQH","created_at":"2026-07-05T03:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:a62d255677bf61549eca77b2ce571cc766d9f1e50a40925d675f97412e65bd1f","target":"graph","created_at":"2026-07-05T03:27:03Z","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/2106.04480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show that approximate reversibility can be learned through a simple surrogate task: ranking randomly sampled trajectory events in chronological order. Intuitively, pairs of events that are always observed in the same order are likely to be separated by an irreversible sequence of actions. Conveniently, learning the temporal order of events can be done in a fully self-supervised way, which we use to estimate the reversibi","authors_text":"Johan Ferret, Matthieu Geist, Nathan Grinsztajn, Olivier Pietquin, Philippe Preux","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T16:07:10Z","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04480","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":"sha256:626053bc403db96f7c4f7fb5631d28306260021028a4fc76a6ea5781d8501a45","target":"record","created_at":"2026-07-05T03:27:03Z","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":"34b28e99baf86f003aae99b68fe36c70dcad9adccf2ea06237379a14390fd6bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T16:07:10Z","title_canon_sha256":"d6f04f6a536cd86bb4e4c144e3c9b0270bb5261094f6a7476e8fa9b5e8c1476b"},"schema_version":"1.0","source":{"id":"2106.04480","kind":"arxiv","version":3}},"canonical_sha256":"2c6360a6075f548955fb78b8cdbe0e715dd21113453e1fb92801eb5ec40be5c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6360a6075f548955fb78b8cdbe0e715dd21113453e1fb92801eb5ec40be5c4","first_computed_at":"2026-07-05T03:27:03.168947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:03.168947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FptBHsenrYDp12qUsLlSxZFoaDe6t05xbLrjwwO4vC1ArI0zRg/6P76wRi+eX7dhhItVaZAfS7HtBGzrkBCFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:03.169430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04480","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:626053bc403db96f7c4f7fb5631d28306260021028a4fc76a6ea5781d8501a45","sha256:a62d255677bf61549eca77b2ce571cc766d9f1e50a40925d675f97412e65bd1f"],"state_sha256":"0467f3002311e6674865e56cce67ae0a037f8992f9afc28f72f149738b79e582"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lcQ0Jq6dVd6FDzijwPqWxT1zJ2E/zdpjGa0Obdobsfg0VnxkPyToigLQ2kslP4LAenW20DjYqalgVtSr9etBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:32:29.391369Z","bundle_sha256":"9e4d05bd68c966bdf233f8c15676713e0726104675f88e3b6700c4e09e0d8659"}}