{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S5UFCUILLB5MCIZDGIXJLRWD27","short_pith_number":"pith:S5UFCUIL","schema_version":"1.0","canonical_sha256":"976851510b587ac12323322e95c6c3d7c0d8974a30e7312daf9da60a1850ae71","source":{"kind":"arxiv","id":"2206.03271","version":2},"attestation_state":"computed","paper":{"title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Stephen James, Zhao Mandi","submitted_at":"2022-06-07T13:24:00Z","abstract_excerpt":"Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However, meta-reinforcement learning (meta-RL) algorithms have thus far been restricted to simple environments with narrow task distributions. Moreover, the paradigm of pretraining followed by fine-tuning to adapt to new tasks has emerged as a simple yet effective solution in supervised and self-supervised learning. This calls into question the benefits of meta-learning app"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.03271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T13:24:00Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"62f4125b882db584c5fd6ed09acb7e3bedb63b4dd5d38a22b3a0d0972bdc6376","abstract_canon_sha256":"f08aa736faba16100a1d9f9ee6d9d0c6ed57e6e2e9599f0f34acce185274d55b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:25.478967Z","signature_b64":"c9PnqTR8xDhSdMOUa1tc14AIbjdTdhga5hOf5cf7RI7RXkP4v6A9GagnKe7rFOr1zPfFLgmAyYcscP3hPSlADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"976851510b587ac12323322e95c6c3d7c0d8974a30e7312daf9da60a1850ae71","last_reissued_at":"2026-07-05T05:42:25.478516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:25.478516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Stephen James, Zhao Mandi","submitted_at":"2022-06-07T13:24:00Z","abstract_excerpt":"Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However, meta-reinforcement learning (meta-RL) algorithms have thus far been restricted to simple environments with narrow task distributions. Moreover, the paradigm of pretraining followed by fine-tuning to adapt to new tasks has emerged as a simple yet effective solution in supervised and self-supervised learning. This calls into question the benefits of meta-learning app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03271","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/2206.03271/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.03271","created_at":"2026-07-05T05:42:25.478573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03271v2","created_at":"2026-07-05T05:42:25.478573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03271","created_at":"2026-07-05T05:42:25.478573+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5UFCUILLB5M","created_at":"2026-07-05T05:42:25.478573+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5UFCUILLB5MCIZD","created_at":"2026-07-05T05:42:25.478573+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5UFCUIL","created_at":"2026-07-05T05:42:25.478573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12547","citing_title":"ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27","json":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27.json","graph_json":"https://pith.science/api/pith-number/S5UFCUILLB5MCIZDGIXJLRWD27/graph.json","events_json":"https://pith.science/api/pith-number/S5UFCUILLB5MCIZDGIXJLRWD27/events.json","paper":"https://pith.science/paper/S5UFCUIL"},"agent_actions":{"view_html":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27","download_json":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27.json","view_paper":"https://pith.science/paper/S5UFCUIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03271&json=true","fetch_graph":"https://pith.science/api/pith-number/S5UFCUILLB5MCIZDGIXJLRWD27/graph.json","fetch_events":"https://pith.science/api/pith-number/S5UFCUILLB5MCIZDGIXJLRWD27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27/action/storage_attestation","attest_author":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27/action/author_attestation","sign_citation":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27/action/citation_signature","submit_replication":"https://pith.science/pith/S5UFCUILLB5MCIZDGIXJLRWD27/action/replication_record"}},"created_at":"2026-07-05T05:42:25.478573+00:00","updated_at":"2026-07-05T05:42:25.478573+00:00"}