{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EATS47GNARHWJ4LWDNNA6PLKLF","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":"adbf8c616016e81d6770b359772280fe299244ca3eccc5c2a05bcc44b3489b3d","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T17:38:23Z","title_canon_sha256":"fb8a7e28be03b2ee33bbad89201dadd243fabb786e47c0552a1c441b379b7d8e"},"schema_version":"1.0","source":{"id":"2411.15931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15931","created_at":"2026-07-05T10:30:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15931v2","created_at":"2026-07-05T10:30:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15931","created_at":"2026-07-05T10:30:58Z"},{"alias_kind":"pith_short_12","alias_value":"EATS47GNARHW","created_at":"2026-07-05T10:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"EATS47GNARHWJ4LW","created_at":"2026-07-05T10:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"EATS47GN","created_at":"2026-07-05T10:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:125180e2eae9c431b302ce7f1d5e669b5fdcb859b8394ad9ace830322442bb0f","target":"graph","created_at":"2026-07-05T10:30:58Z","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/2411.15931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A number of different architectures and loss functions have been applied to the problem of self-supervised learning (SSL), with the goal of developing embeddings that provide the best possible pre-training for as-yet-unknown, lightly supervised downstream tasks. One of these SSL criteria is to maximize the entropy of a set of embeddings in some compact space. But the goal of maximizing the embedding entropy often depends -- whether explicitly or implicitly -- upon high dimensional entropy estimates, which typically perform poorly in more than a few dimensions. In this paper, we motivate an eff","authors_text":"Deep Chakraborty, Erik Learned-Miller, Tim G. J. Rudner, Yann LeCun","cross_cats":["cs.CV","cs.IT","math.IT","stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T17:38:23Z","title":"Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15931","kind":"arxiv","version":2},"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":"sha256:0e5420fdd61cc034a3669ccf257134667513a53be2b650741d86d0d8b45b3fcb","target":"record","created_at":"2026-07-05T10:30:58Z","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":"adbf8c616016e81d6770b359772280fe299244ca3eccc5c2a05bcc44b3489b3d","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T17:38:23Z","title_canon_sha256":"fb8a7e28be03b2ee33bbad89201dadd243fabb786e47c0552a1c441b379b7d8e"},"schema_version":"1.0","source":{"id":"2411.15931","kind":"arxiv","version":2}},"canonical_sha256":"20272e7ccd044f64f1761b5a0f3d6a5966cfe13f03555baa00200c744c716f73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20272e7ccd044f64f1761b5a0f3d6a5966cfe13f03555baa00200c744c716f73","first_computed_at":"2026-07-05T10:30:58.530606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:58.530606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UJc9xRQ/nl8cYgvXK52REJvYza9iV/b5RULzICZk5Iq8kAMMK+zqoMqf33JoUraV1yueV5bu2v4lYAquG5DXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:58.531114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e5420fdd61cc034a3669ccf257134667513a53be2b650741d86d0d8b45b3fcb","sha256:125180e2eae9c431b302ce7f1d5e669b5fdcb859b8394ad9ace830322442bb0f"],"state_sha256":"ebfd428992b6c01a74b6850abe93183c13dfcf5eea20ff38ff58d581ab025fd5"}