{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RWRXQZKESPIOAKAHLZVSEOT7H2","short_pith_number":"pith:RWRXQZKE","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"},"canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","source":{"kind":"arxiv","id":"2605.25821","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25821","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25821v1","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25821","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"RWRXQZKESPIO","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"RWRXQZKESPIOAKAH","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"RWRXQZKE","created_at":"2026-05-26T02:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RWRXQZKESPIOAKAHLZVSEOT7H2","target":"record","payload":{"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"},"canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","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"},"source_kind":"arxiv","source_id":"2605.25821","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Orc/IxBYybIwWFvMGbZuZ06E8PO/eMdEWDnkr7p219IYNydXfByu2/B5zK8cmI3mQR/nYvRpbLrjKOcHurmMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:35:35.291254Z"},"content_sha256":"b1a04bffb87fe199bff317f689ebbcde11ea1aa8a996488132c4b9863f751c8e","schema_version":"1.0","event_id":"sha256:b1a04bffb87fe199bff317f689ebbcde11ea1aa8a996488132c4b9863f751c8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RWRXQZKESPIOAKAHLZVSEOT7H2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkiPF3ABtwc6b+LFDE8ki+LTwD4dJOfTHmmlsaH9rpi58Bn8U88niDZhye1iOpQx/luDf3rZv/+OafsjT173Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:35:35.291661Z"},"content_sha256":"b62c2a5e470cc442dc8dea6ee36f8f0c5e344da91d73c6c9b0241f0432140386","schema_version":"1.0","event_id":"sha256:b62c2a5e470cc442dc8dea6ee36f8f0c5e344da91d73c6c9b0241f0432140386"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/bundle.json","state_url":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-01T08:35:35Z","links":{"resolver":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2","bundle":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/bundle.json","state":"https://pith.science/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWRXQZKESPIOAKAHLZVSEOT7H2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RWRXQZKESPIOAKAHLZVSEOT7H2","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":"64e30cad481085d0adee91c16607a74a968f8a0aff5aefbde7d52f0661b16004","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T13:19:12Z","title_canon_sha256":"6ed94fe0cce772476d5b913410372e622b2cac2c0e8f833cd1bdaaf76fafca3d"},"schema_version":"1.0","source":{"id":"2605.25821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25821","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25821v1","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25821","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"RWRXQZKESPIO","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"RWRXQZKESPIOAKAH","created_at":"2026-05-26T02:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"RWRXQZKE","created_at":"2026-05-26T02:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:b62c2a5e470cc442dc8dea6ee36f8f0c5e344da91d73c6c9b0241f0432140386","target":"graph","created_at":"2026-05-26T02:05:13Z","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/2605.25821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akang Wang, Huafeng Li, Xili Deng, Yi Zhao, Yonghang Tai, Zhanxuan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T13:19:12Z","title":"[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25821","kind":"arxiv","version":1},"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:b1a04bffb87fe199bff317f689ebbcde11ea1aa8a996488132c4b9863f751c8e","target":"record","created_at":"2026-05-26T02:05:13Z","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":"64e30cad481085d0adee91c16607a74a968f8a0aff5aefbde7d52f0661b16004","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T13:19:12Z","title_canon_sha256":"6ed94fe0cce772476d5b913410372e622b2cac2c0e8f833cd1bdaaf76fafca3d"},"schema_version":"1.0","source":{"id":"2605.25821","kind":"arxiv","version":1}},"canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8da378654493d0e028075e6b223a7f3e92378e7ff386dbcc08c3f8ba03babe08","first_computed_at":"2026-05-26T02:05:13.342586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:13.342586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tC4OUKooGLMYz73gJoZH7S8zUt8px8HBbYJ9PP5bjoexyy4NsuKMWZrhoWDX3pYElWgnncnyWqIZvR2Hqfi/CA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:13.343367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1a04bffb87fe199bff317f689ebbcde11ea1aa8a996488132c4b9863f751c8e","sha256:b62c2a5e470cc442dc8dea6ee36f8f0c5e344da91d73c6c9b0241f0432140386"],"state_sha256":"2d8d122299f7b7dbaaddd8fd707297713d98a9e1cc16d45684270ed898c645e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O8kRcbnDWF78u0CSQ8YytRQlypBrftoJKNsGJc6NtEHw4ZZ5K68rT3gCKbprJE7GnoWS82XSiP/E2D2dkaAcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T08:35:35.294269Z","bundle_sha256":"3ca5cf7ee6995ac356379faefc83c01813ba26a4c71c48f471b83fa9cbbc072c"}}