{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3TJ5I6KJSZWRW34BA2RSQHEGEJ","short_pith_number":"pith:3TJ5I6KJ","schema_version":"1.0","canonical_sha256":"dcd3d47949966d1b6f8106a3281c86226b2402bfec16babb677e2b027414a939","source":{"kind":"arxiv","id":"2210.11464","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning via Maximum Entropy Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shengjin Wang, Xin Liu, Yali Li, Zhongdao Wang","submitted_at":"2022-10-20T17:58:30Z","abstract_excerpt":"A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the le"},"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":"2210.11464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T17:58:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73aab36753f93e65a4b45b07255ce763295faac7575635c762a960361852c4ba","abstract_canon_sha256":"7323201b1059f51cbc85b451e3acae5580ddc2652622b60d9d10bf7d9e8a3a03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:48.895685Z","signature_b64":"Hosfahck+1xhAUgB4oexD6GDkCLizMRaH1I/fSmKGO+qh/OIG9F5cASky/6/YcIdOKtfs7jDwkSw1Ngp087rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcd3d47949966d1b6f8106a3281c86226b2402bfec16babb677e2b027414a939","last_reissued_at":"2026-07-05T05:08:48.895193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:48.895193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning via Maximum Entropy Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shengjin Wang, Xin Liu, Yali Li, Zhongdao Wang","submitted_at":"2022-10-20T17:58:30Z","abstract_excerpt":"A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11464","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/2210.11464/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":"2210.11464","created_at":"2026-07-05T05:08:48.895254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11464v1","created_at":"2026-07-05T05:08:48.895254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11464","created_at":"2026-07-05T05:08:48.895254+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TJ5I6KJSZWR","created_at":"2026-07-05T05:08:48.895254+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TJ5I6KJSZWRW34B","created_at":"2026-07-05T05:08:48.895254+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TJ5I6KJ","created_at":"2026-07-05T05:08:48.895254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13596","citing_title":"A Generalized Learning Framework for Self-Supervised Contrastive Learning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ","json":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ.json","graph_json":"https://pith.science/api/pith-number/3TJ5I6KJSZWRW34BA2RSQHEGEJ/graph.json","events_json":"https://pith.science/api/pith-number/3TJ5I6KJSZWRW34BA2RSQHEGEJ/events.json","paper":"https://pith.science/paper/3TJ5I6KJ"},"agent_actions":{"view_html":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ","download_json":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ.json","view_paper":"https://pith.science/paper/3TJ5I6KJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11464&json=true","fetch_graph":"https://pith.science/api/pith-number/3TJ5I6KJSZWRW34BA2RSQHEGEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3TJ5I6KJSZWRW34BA2RSQHEGEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ/action/storage_attestation","attest_author":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ/action/author_attestation","sign_citation":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ/action/citation_signature","submit_replication":"https://pith.science/pith/3TJ5I6KJSZWRW34BA2RSQHEGEJ/action/replication_record"}},"created_at":"2026-07-05T05:08:48.895254+00:00","updated_at":"2026-07-05T05:08:48.895254+00:00"}