{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RWRXQZKESPIOAKAHLZVSEOT7H2","short_pith_number":"pith:RWRXQZKE","schema_version":"1.0","canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","source":{"kind":"arxiv","id":"2605.25821","version":1},"attestation_state":"computed","paper":{"title":"[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akang Wang, Huafeng Li, Xili Deng, Yi Zhao, Yonghang Tai, Zhanxuan Hu","submitted_at":"2026-05-25T13:19:12Z","abstract_excerpt":"Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that the [CLS] token, as a single global visual representation, is insufficient to faithfully encode diverse targets with varying scales, contexts, and co-occurrence patterns. To address this limitation, we present a new multi-label image recognition framework, termed PIAA, which formulates prediction as Patch-level Inference followed by Adaptive Aggregation. Spec"},"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":"2605.25821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T13:19:12Z","cross_cats_sorted":[],"title_canon_sha256":"6ed94fe0cce772476d5b913410372e622b2cac2c0e8f833cd1bdaaf76fafca3d","abstract_canon_sha256":"64e30cad481085d0adee91c16607a74a968f8a0aff5aefbde7d52f0661b16004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:13.343367Z","signature_b64":"tC4OUKooGLMYz73gJoZH7S8zUt8px8HBbYJ9PP5bjoexyy4NsuKMWZrhoWDX3pYElWgnncnyWqIZvR2Hqfi/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","last_reissued_at":"2026-05-26T02:05:13.342586Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:13.342586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akang Wang, Huafeng Li, Xili Deng, Yi Zhao, Yonghang Tai, Zhanxuan Hu","submitted_at":"2026-05-25T13:19:12Z","abstract_excerpt":"Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that the [CLS] token, as a single global visual representation, is insufficient to faithfully encode diverse targets with varying scales, contexts, and co-occurrence patterns. To address this limitation, we present a new multi-label image recognition framework, termed PIAA, which formulates prediction as Patch-level Inference followed by Adaptive Aggregation. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25821","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/2605.25821/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":"2605.25821","created_at":"2026-05-26T02:05:13.342702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25821v1","created_at":"2026-05-26T02:05:13.342702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25821","created_at":"2026-05-26T02:05:13.342702+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWRXQZKESPIO","created_at":"2026-05-26T02:05:13.342702+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWRXQZKESPIOAKAH","created_at":"2026-05-26T02:05:13.342702+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWRXQZKE","created_at":"2026-05-26T02:05:13.342702+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/RWRXQZKESPIOAKAHLZVSEOT7H2","json":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2.json","graph_json":"https://pith.science/api/pith-number/RWRXQZKESPIOAKAHLZVSEOT7H2/graph.json","events_json":"https://pith.science/api/pith-number/RWRXQZKESPIOAKAHLZVSEOT7H2/events.json","paper":"https://pith.science/paper/RWRXQZKE"},"agent_actions":{"view_html":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2","download_json":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2.json","view_paper":"https://pith.science/paper/RWRXQZKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25821&json=true","fetch_graph":"https://pith.science/api/pith-number/RWRXQZKESPIOAKAHLZVSEOT7H2/graph.json","fetch_events":"https://pith.science/api/pith-number/RWRXQZKESPIOAKAHLZVSEOT7H2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/action/storage_attestation","attest_author":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/action/author_attestation","sign_citation":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/action/citation_signature","submit_replication":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/action/replication_record"}},"created_at":"2026-05-26T02:05:13.342702+00:00","updated_at":"2026-05-26T02:05:13.342702+00:00"}