{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5DWOT3DN4MAZGK5OPZ2QZSWSL2","short_pith_number":"pith:5DWOT3DN","canonical_record":{"source":{"id":"2606.11626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T03:41:50Z","cross_cats_sorted":[],"title_canon_sha256":"4db330194d6925bd67b74e95c68c4234de7de5bdfefa83fd45f99f653215275b","abstract_canon_sha256":"a1f69a59e21c897f668c4761b4a91cbb69054f47ddf43805add50a5b54cba732"},"schema_version":"1.0"},"canonical_sha256":"e8ece9ec6de301932bae7e750ccad25ea6594ba3465eef89aeb5b0d9c7178579","source":{"kind":"arxiv","id":"2606.11626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11626","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11626v1","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11626","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"5DWOT3DN4MAZ","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"5DWOT3DN4MAZGK5O","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"5DWOT3DN","created_at":"2026-06-11T01:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5DWOT3DN4MAZGK5OPZ2QZSWSL2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T03:41:50Z","cross_cats_sorted":[],"title_canon_sha256":"4db330194d6925bd67b74e95c68c4234de7de5bdfefa83fd45f99f653215275b","abstract_canon_sha256":"a1f69a59e21c897f668c4761b4a91cbb69054f47ddf43805add50a5b54cba732"},"schema_version":"1.0"},"canonical_sha256":"e8ece9ec6de301932bae7e750ccad25ea6594ba3465eef89aeb5b0d9c7178579","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:59.679641Z","signature_b64":"PkWErnnb7tqHjymnkbS6+BOJIrBFAcFX7DKW0j2flB6hgZy7ntBbByfU/BH3SAVOYQJeLvJFXdccD4OzZSuPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ece9ec6de301932bae7e750ccad25ea6594ba3465eef89aeb5b0d9c7178579","last_reissued_at":"2026-06-11T01:09:59.678941Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:59.678941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11626","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":"2026-06-11T01:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urE9DyZB0C+cW3Gmgua/anCbWTLJd7pdAJ9l12gYhIHdB5EtmnEfXqsg4ikVf6MKSTS5g1ifJSOwR9CPxcm0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T06:58:03.671249Z"},"content_sha256":"2785eb6bc57367173fab49ca97034d65bca711ad14d5e230a8274ef4b5bfe0b4","schema_version":"1.0","event_id":"sha256:2785eb6bc57367173fab49ca97034d65bca711ad14d5e230a8274ef4b5bfe0b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5DWOT3DN4MAZGK5OPZ2QZSWSL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Chen, Jia Li, Jingyu Zhou, Yifan Zhao","submitted_at":"2026-06-10T03:41:50Z","abstract_excerpt":"Understanding multi-label images remains a challenging task in computer vision. With the rapid progress of vision-language multimodal learning, vision-language models (VLMs) enable zero-shot recognition without labeled data. However, due to their intrinsic design, these models often prioritize the most iconic object and omit other contextual positives. This intrinsic bias conflicts with the nature of multi-label learning, thereby limiting their applicability. In this work, we propose an unsupervised framework that adapts VLMs from iconic recognition toward inclusive understanding, enabling lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11626","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/2606.11626/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":"2026-06-11T01:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIXOYUtJJF2ThJw4kA6FI2H+NSdjZ3PL5DQastsfsrYtyGVOYAfPhrrlzH5477C/lgBxBEfV03o3d5z/sDrCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T06:58:03.671660Z"},"content_sha256":"4c982f817eda629f06a457638521de6164c5e0759b05791bbf2f8943ffe2ffe7","schema_version":"1.0","event_id":"sha256:4c982f817eda629f06a457638521de6164c5e0759b05791bbf2f8943ffe2ffe7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/bundle.json","state_url":"https://pith.science/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/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":"2026-07-05T06:58:03Z","links":{"resolver":"https://pith.science/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2","bundle":"https://pith.science/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/bundle.json","state":"https://pith.science/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DWOT3DN4MAZGK5OPZ2QZSWSL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5DWOT3DN4MAZGK5OPZ2QZSWSL2","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":"a1f69a59e21c897f668c4761b4a91cbb69054f47ddf43805add50a5b54cba732","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T03:41:50Z","title_canon_sha256":"4db330194d6925bd67b74e95c68c4234de7de5bdfefa83fd45f99f653215275b"},"schema_version":"1.0","source":{"id":"2606.11626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11626","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11626v1","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11626","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"5DWOT3DN4MAZ","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"5DWOT3DN4MAZGK5O","created_at":"2026-06-11T01:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"5DWOT3DN","created_at":"2026-06-11T01:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:4c982f817eda629f06a457638521de6164c5e0759b05791bbf2f8943ffe2ffe7","target":"graph","created_at":"2026-06-11T01:09:59Z","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/2606.11626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding multi-label images remains a challenging task in computer vision. With the rapid progress of vision-language multimodal learning, vision-language models (VLMs) enable zero-shot recognition without labeled data. However, due to their intrinsic design, these models often prioritize the most iconic object and omit other contextual positives. This intrinsic bias conflicts with the nature of multi-label learning, thereby limiting their applicability. In this work, we propose an unsupervised framework that adapts VLMs from iconic recognition toward inclusive understanding, enabling lab","authors_text":"Cheng Chen, Jia Li, Jingyu Zhou, Yifan Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T03:41:50Z","title":"Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11626","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":"sha256:2785eb6bc57367173fab49ca97034d65bca711ad14d5e230a8274ef4b5bfe0b4","target":"record","created_at":"2026-06-11T01:09:59Z","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":"a1f69a59e21c897f668c4761b4a91cbb69054f47ddf43805add50a5b54cba732","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T03:41:50Z","title_canon_sha256":"4db330194d6925bd67b74e95c68c4234de7de5bdfefa83fd45f99f653215275b"},"schema_version":"1.0","source":{"id":"2606.11626","kind":"arxiv","version":1}},"canonical_sha256":"e8ece9ec6de301932bae7e750ccad25ea6594ba3465eef89aeb5b0d9c7178579","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8ece9ec6de301932bae7e750ccad25ea6594ba3465eef89aeb5b0d9c7178579","first_computed_at":"2026-06-11T01:09:59.678941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:59.678941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PkWErnnb7tqHjymnkbS6+BOJIrBFAcFX7DKW0j2flB6hgZy7ntBbByfU/BH3SAVOYQJeLvJFXdccD4OzZSuPAw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:59.679641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2785eb6bc57367173fab49ca97034d65bca711ad14d5e230a8274ef4b5bfe0b4","sha256:4c982f817eda629f06a457638521de6164c5e0759b05791bbf2f8943ffe2ffe7"],"state_sha256":"1b2dc9f58fb502f4bf20fa077607f34eb445c7a5c757e4bcdc90232c057a3da7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"awXfZWOfoefk5TBErD3mCaEwn3RqOLhkr/SDunNc4jbHBECYD1vJ8OBDZJK6Fkhvl62kN7naJpOnfHG9fPGcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T06:58:03.674033Z","bundle_sha256":"ef9128f5e1aea264d3e575467e1ee5c0f260aa39fa57cc2611623d0493c97f9c"}}