{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UCGKPIXFWV62FDH3QTFVIEMOSF","short_pith_number":"pith:UCGKPIXF","schema_version":"1.0","canonical_sha256":"a08ca7a2e5b57da28cfb84cb54118e915d1590b96c79315f9fbce5a0111db2e0","source":{"kind":"arxiv","id":"2204.13207","version":1},"attestation_state":"computed","paper":{"title":"Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Chetan Ramaiah, Ran Xu, Shu Zhang","submitted_at":"2022-04-27T21:41:44Z","abstract_excerpt":"Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint. The loss function is data driven and automatically adapts to arbitrary multi-label "},"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":"2204.13207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-27T21:41:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"205af677754a597035563f1f462c9c6245573fa9c5ef808af17d6a8e792fcc8b","abstract_canon_sha256":"32d51d1ca2b2cb46512124f1b933561f61593c84c71df10c1957cb2fde08ffbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:32.200219Z","signature_b64":"thIFTfw8CFNAiCOJBcihDwC0ku8FJF6VY2UDNP4WLUUJQhRhI82TWLFg7LFIpW/AuF5QoXG4pb1h8GNc3eFuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08ca7a2e5b57da28cfb84cb54118e915d1590b96c79315f9fbce5a0111db2e0","last_reissued_at":"2026-07-05T04:18:32.199740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:32.199740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Chetan Ramaiah, Ran Xu, Shu Zhang","submitted_at":"2022-04-27T21:41:44Z","abstract_excerpt":"Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint. The loss function is data driven and automatically adapts to arbitrary multi-label "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13207","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/2204.13207/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":"2204.13207","created_at":"2026-07-05T04:18:32.199797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13207v1","created_at":"2026-07-05T04:18:32.199797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13207","created_at":"2026-07-05T04:18:32.199797+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCGKPIXFWV62","created_at":"2026-07-05T04:18:32.199797+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCGKPIXFWV62FDH3","created_at":"2026-07-05T04:18:32.199797+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCGKPIXF","created_at":"2026-07-05T04:18:32.199797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF","json":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF.json","graph_json":"https://pith.science/api/pith-number/UCGKPIXFWV62FDH3QTFVIEMOSF/graph.json","events_json":"https://pith.science/api/pith-number/UCGKPIXFWV62FDH3QTFVIEMOSF/events.json","paper":"https://pith.science/paper/UCGKPIXF"},"agent_actions":{"view_html":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF","download_json":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF.json","view_paper":"https://pith.science/paper/UCGKPIXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13207&json=true","fetch_graph":"https://pith.science/api/pith-number/UCGKPIXFWV62FDH3QTFVIEMOSF/graph.json","fetch_events":"https://pith.science/api/pith-number/UCGKPIXFWV62FDH3QTFVIEMOSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF/action/storage_attestation","attest_author":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF/action/author_attestation","sign_citation":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF/action/citation_signature","submit_replication":"https://pith.science/pith/UCGKPIXFWV62FDH3QTFVIEMOSF/action/replication_record"}},"created_at":"2026-07-05T04:18:32.199797+00:00","updated_at":"2026-07-05T04:18:32.199797+00:00"}