{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W45XNSKZ6ML6X7RFU7ZV46TMS2","short_pith_number":"pith:W45XNSKZ","schema_version":"1.0","canonical_sha256":"b73b76c959f317ebfe25a7f35e7a6c968d9903b8e6f948a0978e4afabe096eaf","source":{"kind":"arxiv","id":"2207.07611","version":1},"attestation_state":"computed","paper":{"title":"Position Prediction as an Effective Pretraining Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Chen Huang, Dan Busbridge, Hanlin Goh, Jason Ramapuram, Joseph Yitan Cheng, Joshua Susskind, Navdeep Jaitly, Shuangfei Zhai, Tatiana Likhomanenko, Walter Talbott","submitted_at":"2022-07-15T17:10:48Z","abstract_excerpt":"Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this representational capacity effectively requires a large amount of data, strong regularization, or both, to mitigate overfitting. Recently, the power of the Transformer has been unlocked by self-supervised pretraining strategies based on masked autoencoders which rely on reconstructing masked inputs, directly, or contrastively from unmasked content. This pr"},"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":"2207.07611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T17:10:48Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"30e03b70a49d6bd79126038db8be1526df0d9408fba43d5475f173744460745b","abstract_canon_sha256":"81af7d94a71786b50bb01a1be97f123d6587716bbed7148052f9ca53f915f3d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:34.514191Z","signature_b64":"7VE52xVU5lMuhCDPCxuAq2vCDj0D8RfQL0ZPesvRBKNMuzTunWiw4sGcMgmkuFTOOrtwpEYQRGdXrYopip9pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b73b76c959f317ebfe25a7f35e7a6c968d9903b8e6f948a0978e4afabe096eaf","last_reissued_at":"2026-07-05T04:40:34.513704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:34.513704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position Prediction as an Effective Pretraining Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Chen Huang, Dan Busbridge, Hanlin Goh, Jason Ramapuram, Joseph Yitan Cheng, Joshua Susskind, Navdeep Jaitly, Shuangfei Zhai, Tatiana Likhomanenko, Walter Talbott","submitted_at":"2022-07-15T17:10:48Z","abstract_excerpt":"Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this representational capacity effectively requires a large amount of data, strong regularization, or both, to mitigate overfitting. Recently, the power of the Transformer has been unlocked by self-supervised pretraining strategies based on masked autoencoders which rely on reconstructing masked inputs, directly, or contrastively from unmasked content. This pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07611","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/2207.07611/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":"2207.07611","created_at":"2026-07-05T04:40:34.513763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07611v1","created_at":"2026-07-05T04:40:34.513763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07611","created_at":"2026-07-05T04:40:34.513763+00:00"},{"alias_kind":"pith_short_12","alias_value":"W45XNSKZ6ML6","created_at":"2026-07-05T04:40:34.513763+00:00"},{"alias_kind":"pith_short_16","alias_value":"W45XNSKZ6ML6X7RF","created_at":"2026-07-05T04:40:34.513763+00:00"},{"alias_kind":"pith_short_8","alias_value":"W45XNSKZ","created_at":"2026-07-05T04:40:34.513763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09963","citing_title":"Learning to Perceive \"Where\": Spatial Pretext Tasks for Robust Self-Supervised Learning","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2","json":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2.json","graph_json":"https://pith.science/api/pith-number/W45XNSKZ6ML6X7RFU7ZV46TMS2/graph.json","events_json":"https://pith.science/api/pith-number/W45XNSKZ6ML6X7RFU7ZV46TMS2/events.json","paper":"https://pith.science/paper/W45XNSKZ"},"agent_actions":{"view_html":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2","download_json":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2.json","view_paper":"https://pith.science/paper/W45XNSKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07611&json=true","fetch_graph":"https://pith.science/api/pith-number/W45XNSKZ6ML6X7RFU7ZV46TMS2/graph.json","fetch_events":"https://pith.science/api/pith-number/W45XNSKZ6ML6X7RFU7ZV46TMS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2/action/storage_attestation","attest_author":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2/action/author_attestation","sign_citation":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2/action/citation_signature","submit_replication":"https://pith.science/pith/W45XNSKZ6ML6X7RFU7ZV46TMS2/action/replication_record"}},"created_at":"2026-07-05T04:40:34.513763+00:00","updated_at":"2026-07-05T04:40:34.513763+00:00"}