{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JUD344YKFP4KK75V6J6NS4MDAM","short_pith_number":"pith:JUD344YK","schema_version":"1.0","canonical_sha256":"4d07be730a2bf8a57fb5f27cd971830316e2db93c36e265812d551c35e07de93","source":{"kind":"arxiv","id":"2607.02909","version":1},"attestation_state":"computed","paper":{"title":"Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hulingxiao He, Yuxin Peng, Zhi Tan","submitted_at":"2026-07-03T03:16:41Z","abstract_excerpt":"Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite their impressive capabilities, large multimodal models (LMMs) often lack taxonomic knowledge, leading to low hierarchical visual recognition (HVR) consistency. These models typically only rely on language modeling objectives during fine-tuning and lack explicit taxonomy-aware regularization. To address this, we propose Hierarchical Representation Regularization ($HiR^2$), a simple plug-and-play regularizer that improves hierarchical consistency in L"},"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":"2607.02909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T03:16:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e28e839ae99d883a2e63a675c30a94cfec5fd174edf7613cf9be1248a3535e02","abstract_canon_sha256":"70f2eda098de03d745a87dd94c468fcd37742175739d895165aa958c8bcc8e4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:36.160149Z","signature_b64":"MvPXh1DRuzyuiHJKAWmb7iY48mIjS0ENn8HVlnUgqdo9dSxpJPMigTky193CELLMgCLt5R6qzwyWlqNSf0NHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d07be730a2bf8a57fb5f27cd971830316e2db93c36e265812d551c35e07de93","last_reissued_at":"2026-07-07T01:16:36.159736Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:36.159736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hulingxiao He, Yuxin Peng, Zhi Tan","submitted_at":"2026-07-03T03:16:41Z","abstract_excerpt":"Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite their impressive capabilities, large multimodal models (LMMs) often lack taxonomic knowledge, leading to low hierarchical visual recognition (HVR) consistency. These models typically only rely on language modeling objectives during fine-tuning and lack explicit taxonomy-aware regularization. To address this, we propose Hierarchical Representation Regularization ($HiR^2$), a simple plug-and-play regularizer that improves hierarchical consistency in L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02909","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/2607.02909/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":"2607.02909","created_at":"2026-07-07T01:16:36.159794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02909v1","created_at":"2026-07-07T01:16:36.159794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02909","created_at":"2026-07-07T01:16:36.159794+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUD344YKFP4K","created_at":"2026-07-07T01:16:36.159794+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUD344YKFP4KK75V","created_at":"2026-07-07T01:16:36.159794+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUD344YK","created_at":"2026-07-07T01:16:36.159794+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/JUD344YKFP4KK75V6J6NS4MDAM","json":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM.json","graph_json":"https://pith.science/api/pith-number/JUD344YKFP4KK75V6J6NS4MDAM/graph.json","events_json":"https://pith.science/api/pith-number/JUD344YKFP4KK75V6J6NS4MDAM/events.json","paper":"https://pith.science/paper/JUD344YK"},"agent_actions":{"view_html":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM","download_json":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM.json","view_paper":"https://pith.science/paper/JUD344YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02909&json=true","fetch_graph":"https://pith.science/api/pith-number/JUD344YKFP4KK75V6J6NS4MDAM/graph.json","fetch_events":"https://pith.science/api/pith-number/JUD344YKFP4KK75V6J6NS4MDAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM/action/storage_attestation","attest_author":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM/action/author_attestation","sign_citation":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM/action/citation_signature","submit_replication":"https://pith.science/pith/JUD344YKFP4KK75V6J6NS4MDAM/action/replication_record"}},"created_at":"2026-07-07T01:16:36.159794+00:00","updated_at":"2026-07-07T01:16:36.159794+00:00"}