{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2TW27HTS6C2MZDCJR54FO3VVK","short_pith_number":"pith:O2TW27HT","schema_version":"1.0","canonical_sha256":"76a76d7cf39785a664624c7bc2bb75aa87e169a937d8d4ba34c8c682310333cb","source":{"kind":"arxiv","id":"2402.14789","version":1},"attestation_state":"computed","paper":{"title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annie S. Chen, Chelsea Finn, Johnathan Xie, Yoonho Lee","submitted_at":"2024-02-22T18:46:22Z","abstract_excerpt":"Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of existing methods are tailored to each domain, such as domain-specific augmentations which reflect the invariances in the target task. While masked modeling is promising as a domain-agnostic framework for self-supervised learning because it does not rely on input augmentations, its mask sampling procedure remains domain-specific. We present Self-gu"},"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":"2402.14789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T18:46:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8916c38ac81c909ed8a518ffd715d3318a699ad65eb74292af8176682b8dfe3d","abstract_canon_sha256":"a82ce9791402c759d40746caa77e6132c47c3ae879a152db31d1036fc826ac6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:14.611281Z","signature_b64":"eqPpE7//CyLVE0Dne3/M4s/MdXJevPTBjSO5P2C2rsBoW0gqt27TVmjJTd1jpnk2ncQJRZfOUHn7VFlRUGGiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a76d7cf39785a664624c7bc2bb75aa87e169a937d8d4ba34c8c682310333cb","last_reissued_at":"2026-07-05T07:48:14.610761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:14.610761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annie S. Chen, Chelsea Finn, Johnathan Xie, Yoonho Lee","submitted_at":"2024-02-22T18:46:22Z","abstract_excerpt":"Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of existing methods are tailored to each domain, such as domain-specific augmentations which reflect the invariances in the target task. While masked modeling is promising as a domain-agnostic framework for self-supervised learning because it does not rely on input augmentations, its mask sampling procedure remains domain-specific. We present Self-gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14789","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/2402.14789/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":"2402.14789","created_at":"2026-07-05T07:48:14.610825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14789v1","created_at":"2026-07-05T07:48:14.610825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14789","created_at":"2026-07-05T07:48:14.610825+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2TW27HTS6C2","created_at":"2026-07-05T07:48:14.610825+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2TW27HTS6C2MZDC","created_at":"2026-07-05T07:48:14.610825+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2TW27HT","created_at":"2026-07-05T07:48:14.610825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16675","citing_title":"On the Out-of-Distribution Generalization of Self-Supervised Learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK","json":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK.json","graph_json":"https://pith.science/api/pith-number/O2TW27HTS6C2MZDCJR54FO3VVK/graph.json","events_json":"https://pith.science/api/pith-number/O2TW27HTS6C2MZDCJR54FO3VVK/events.json","paper":"https://pith.science/paper/O2TW27HT"},"agent_actions":{"view_html":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK","download_json":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK.json","view_paper":"https://pith.science/paper/O2TW27HT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14789&json=true","fetch_graph":"https://pith.science/api/pith-number/O2TW27HTS6C2MZDCJR54FO3VVK/graph.json","fetch_events":"https://pith.science/api/pith-number/O2TW27HTS6C2MZDCJR54FO3VVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK/action/storage_attestation","attest_author":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK/action/author_attestation","sign_citation":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK/action/citation_signature","submit_replication":"https://pith.science/pith/O2TW27HTS6C2MZDCJR54FO3VVK/action/replication_record"}},"created_at":"2026-07-05T07:48:14.610825+00:00","updated_at":"2026-07-05T07:48:14.610825+00:00"}