{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FP4IWC3F7BGFVLI6Q2OOU6ANZD","short_pith_number":"pith:FP4IWC3F","canonical_record":{"source":{"id":"2102.13515","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-24T16:51:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"00210d87d1d4ea19880cad732199ca36f7c91d68f024dc92de6ade84fd6f1a58","abstract_canon_sha256":"f3f9fa27432e3a1d4ff8e94d026ff8e3f3518e5237291a2b546d0c5663c960b6"},"schema_version":"1.0"},"canonical_sha256":"2bf88b0b65f84c5aad1e869cea780dc8f6353ff19386348647b0f32688c45f15","source":{"kind":"arxiv","id":"2102.13515","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.13515","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.13515v3","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13515","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"FP4IWC3F7BGF","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"FP4IWC3F7BGFVLI6","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"FP4IWC3F","created_at":"2026-07-05T02:47:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FP4IWC3F7BGFVLI6Q2OOU6ANZD","target":"record","payload":{"canonical_record":{"source":{"id":"2102.13515","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-24T16:51:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"00210d87d1d4ea19880cad732199ca36f7c91d68f024dc92de6ade84fd6f1a58","abstract_canon_sha256":"f3f9fa27432e3a1d4ff8e94d026ff8e3f3518e5237291a2b546d0c5663c960b6"},"schema_version":"1.0"},"canonical_sha256":"2bf88b0b65f84c5aad1e869cea780dc8f6353ff19386348647b0f32688c45f15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:05.274298Z","signature_b64":"VoUpPb4BTYM9tM3qWVxwfTxmL7f4lXbq52mVe54YZumw7V8voTI2YieEIirv9yTtbPuflxVoJujYXsujxwiFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf88b0b65f84c5aad1e869cea780dc8f6353ff19386348647b0f32688c45f15","last_reissued_at":"2026-07-05T02:47:05.273388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:05.273388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.13515","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":"2026-07-05T02:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+yblhyCClzhAXkFPXc3pkxULnlUtFgWvZ5lyDScrmwlY6rwtGeYEosNixDCRG3Ht/CapAvrPogXrJJW2y6QCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:21:11.998769Z"},"content_sha256":"264ecf5f783d81d8bc327e4d7c507c8f1bf1eaf6113e8bff4c54fd022f97da23","schema_version":"1.0","event_id":"sha256:264ecf5f783d81d8bc327e4d7c507c8f1bf1eaf6113e8bff4c54fd022f97da23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FP4IWC3F7BGFVLI6Q2OOU6ANZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Vitvitskyi, Andre Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen, Steven Kapturowski, V\\'ictor Campos","submitted_at":"2021-02-24T16:51:02Z","abstract_excerpt":"Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an unsupervised pre-training phase is often transferred by fine-tuning neural network weights once rewards are exposed, as is common practice in supervised domains. Given the nature of the reinforcement learning problem, we argue that standard fine-tuning strategies alone are not enough for efficient transfer in challenging domains. We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13515","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/2102.13515/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":"2026-07-05T02:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gco93UpQXnEKD1+GBOD0OHeeYOAZQ4/LHlHmIh15RavPCQdSO3DcMRmqsPSoj5d6MTzyzp3BQMpW+Es+qFIRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:21:11.999338Z"},"content_sha256":"0ed4d161daf65324e0362bd6532705e2797395374005f2265d92ce6d99caa6a5","schema_version":"1.0","event_id":"sha256:0ed4d161daf65324e0362bd6532705e2797395374005f2265d92ce6d99caa6a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/bundle.json","state_url":"https://pith.science/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/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":"2026-08-22T22:21:12Z","links":{"resolver":"https://pith.science/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD","bundle":"https://pith.science/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/bundle.json","state":"https://pith.science/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FP4IWC3F7BGFVLI6Q2OOU6ANZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FP4IWC3F7BGFVLI6Q2OOU6ANZD","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":"f3f9fa27432e3a1d4ff8e94d026ff8e3f3518e5237291a2b546d0c5663c960b6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-24T16:51:02Z","title_canon_sha256":"00210d87d1d4ea19880cad732199ca36f7c91d68f024dc92de6ade84fd6f1a58"},"schema_version":"1.0","source":{"id":"2102.13515","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.13515","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.13515v3","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13515","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"FP4IWC3F7BGF","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"FP4IWC3F7BGFVLI6","created_at":"2026-07-05T02:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"FP4IWC3F","created_at":"2026-07-05T02:47:05Z"}],"graph_snapshots":[{"event_id":"sha256:0ed4d161daf65324e0362bd6532705e2797395374005f2265d92ce6d99caa6a5","target":"graph","created_at":"2026-07-05T02:47:05Z","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/2102.13515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an unsupervised pre-training phase is often transferred by fine-tuning neural network weights once rewards are exposed, as is common practice in supervised domains. Given the nature of the reinforcement learning problem, we argue that standard fine-tuning strategies alone are not enough for efficient transfer in challenging domains. We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for ex","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Vitvitskyi, Andre Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen, Steven Kapturowski, V\\'ictor Campos","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-24T16:51:02Z","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13515","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":"sha256:264ecf5f783d81d8bc327e4d7c507c8f1bf1eaf6113e8bff4c54fd022f97da23","target":"record","created_at":"2026-07-05T02:47:05Z","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":"f3f9fa27432e3a1d4ff8e94d026ff8e3f3518e5237291a2b546d0c5663c960b6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-24T16:51:02Z","title_canon_sha256":"00210d87d1d4ea19880cad732199ca36f7c91d68f024dc92de6ade84fd6f1a58"},"schema_version":"1.0","source":{"id":"2102.13515","kind":"arxiv","version":3}},"canonical_sha256":"2bf88b0b65f84c5aad1e869cea780dc8f6353ff19386348647b0f32688c45f15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bf88b0b65f84c5aad1e869cea780dc8f6353ff19386348647b0f32688c45f15","first_computed_at":"2026-07-05T02:47:05.273388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:05.273388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VoUpPb4BTYM9tM3qWVxwfTxmL7f4lXbq52mVe54YZumw7V8voTI2YieEIirv9yTtbPuflxVoJujYXsujxwiFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:05.274298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.13515","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:264ecf5f783d81d8bc327e4d7c507c8f1bf1eaf6113e8bff4c54fd022f97da23","sha256:0ed4d161daf65324e0362bd6532705e2797395374005f2265d92ce6d99caa6a5"],"state_sha256":"38b97b8d47dc31bd22847530e4bb2fc3b0f0fea99d2ed206d5bf8f5f66fb5e57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O84U44y7JR5XVuVJnWwyv2sLQEvSu7l6Tot5XAB7c6x/z5fm4aJWr9dzKjlS0a0maq4ZT2bLOy4VoeiTYX0wDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:21:12.003427Z","bundle_sha256":"4e9be9a18649888988f7ea77b0f06259a2238398821b414c38da18e1608d878b"}}