{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CEIOA2FPM5EM6H43FVPZ6633F","short_pith_number":"pith:2CEIOA2F","schema_version":"1.0","canonical_sha256":"d0888703457b3a4678fcd96afcfbdbd947b08015ac89f007eee35695099c998f","source":{"kind":"arxiv","id":"2410.23200","version":1},"attestation_state":"computed","paper":{"title":"HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ghassan AlRegib, Kiran Kokilepersaud, Mohit Prabhushankar, Seulgi Kim","submitted_at":"2024-10-30T16:49:59Z","abstract_excerpt":"In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some invariance term to ensure consistency between similar samples and a regularization term to prevent global dimensional collapse. Dimensional collapse refers to data representations spanning a lower-dimensional subspace. Recent work has demonstrated that the representation space of these algorithms gradually reflects a semantic hierarchical structure as training pro"},"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":"2410.23200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T16:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"c597d60cced39a0bdcdd43b0c984e727920e3656cbfb6277bc2d7975c0004108","abstract_canon_sha256":"faabf4318edc9dbca1ae04712b8deaf1368c6b7332511a94a20f868f60390a31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:42.324301Z","signature_b64":"XPaSMF0AljdLBInNRK61en+epEgKVKAL3SZfxOmO9vGDspWxr9Xn5R3pGDrvIRnRw5ghH2M2E7Wd5KJn2IyyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0888703457b3a4678fcd96afcfbdbd947b08015ac89f007eee35695099c998f","last_reissued_at":"2026-07-05T09:28:42.323838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:42.323838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ghassan AlRegib, Kiran Kokilepersaud, Mohit Prabhushankar, Seulgi Kim","submitted_at":"2024-10-30T16:49:59Z","abstract_excerpt":"In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some invariance term to ensure consistency between similar samples and a regularization term to prevent global dimensional collapse. Dimensional collapse refers to data representations spanning a lower-dimensional subspace. Recent work has demonstrated that the representation space of these algorithms gradually reflects a semantic hierarchical structure as training pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23200","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/2410.23200/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":"2410.23200","created_at":"2026-07-05T09:28:42.323894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23200v1","created_at":"2026-07-05T09:28:42.323894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23200","created_at":"2026-07-05T09:28:42.323894+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CEIOA2FPM5E","created_at":"2026-07-05T09:28:42.323894+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CEIOA2FPM5EM6H4","created_at":"2026-07-05T09:28:42.323894+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CEIOA2F","created_at":"2026-07-05T09:28:42.323894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16264","citing_title":"Information Router for Mitigating Modality Dominance in Vision-Language Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F","json":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F.json","graph_json":"https://pith.science/api/pith-number/2CEIOA2FPM5EM6H43FVPZ6633F/graph.json","events_json":"https://pith.science/api/pith-number/2CEIOA2FPM5EM6H43FVPZ6633F/events.json","paper":"https://pith.science/paper/2CEIOA2F"},"agent_actions":{"view_html":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F","download_json":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F.json","view_paper":"https://pith.science/paper/2CEIOA2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23200&json=true","fetch_graph":"https://pith.science/api/pith-number/2CEIOA2FPM5EM6H43FVPZ6633F/graph.json","fetch_events":"https://pith.science/api/pith-number/2CEIOA2FPM5EM6H43FVPZ6633F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F/action/storage_attestation","attest_author":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F/action/author_attestation","sign_citation":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F/action/citation_signature","submit_replication":"https://pith.science/pith/2CEIOA2FPM5EM6H43FVPZ6633F/action/replication_record"}},"created_at":"2026-07-05T09:28:42.323894+00:00","updated_at":"2026-07-05T09:28:42.323894+00:00"}