{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KTED72D2BSWSHOMSVKHTOSJO3C","short_pith_number":"pith:KTED72D2","canonical_record":{"source":{"id":"2407.04603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T15:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"9920b835ca383afac2800bc38f19bd785cad1f914463ab756d746c212fbd892a","abstract_canon_sha256":"959f9a22694fb09305c2ca5dd6a67f2bdc6176ee556828f0f6fd32f793db4adc"},"schema_version":"1.0"},"canonical_sha256":"54c83fe87a0cad23b992aa8f37492ed89ecd453ca93e56ddac9eb674f8e47c62","source":{"kind":"arxiv","id":"2407.04603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04603","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04603v2","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04603","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"KTED72D2BSWS","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"KTED72D2BSWSHOMS","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"KTED72D2","created_at":"2026-07-05T09:16:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KTED72D2BSWSHOMSVKHTOSJO3C","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T15:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"9920b835ca383afac2800bc38f19bd785cad1f914463ab756d746c212fbd892a","abstract_canon_sha256":"959f9a22694fb09305c2ca5dd6a67f2bdc6176ee556828f0f6fd32f793db4adc"},"schema_version":"1.0"},"canonical_sha256":"54c83fe87a0cad23b992aa8f37492ed89ecd453ca93e56ddac9eb674f8e47c62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:19.427770Z","signature_b64":"aKQswUfLlrnKbMElpHZxZNNkjrtHQVK+0bWY4Clcqq63ScMujEUB8p0W+/ifnXh5FVfdjje0V/JB7Va322JSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54c83fe87a0cad23b992aa8f37492ed89ecd453ca93e56ddac9eb674f8e47c62","last_reissued_at":"2026-07-05T09:16:19.427163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:19.427163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04603","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SqZ9xdESOUtB0fXZ9Z49tHLEMYjU1XEFxCryUTMtT4Fi42FusA/A6pem8n43vjQYB2iMulsLfc4/Powpg2V2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:04:15.020699Z"},"content_sha256":"04cd22e2234a67104ba43027fa985ad09fcaed443007e7be9a9a2a238921f046","schema_version":"1.0","event_id":"sha256:04cd22e2234a67104ba43027fa985ad09fcaed443007e7be9a9a2a238921f046"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KTED72D2BSWSHOMSVKHTOSJO3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Limin Wang, Yuhan Zhu, Yuyang Ji, Zhiyu Zhao","submitted_at":"2024-07-05T15:52:23Z","abstract_excerpt":"Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks. However, we often fail to fully unleash their potential when adapting them for new concept understanding due to limited information on new classes. To address this limitation, we introduce a novel adaptation framework, AWT (Augment, Weight, then Transport). AWT comprises three key components: augmenting inputs with diverse visual perspectives and enriched class descriptions through image transformations and language models; dynamically weighting inputs based on the prediction entropy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04603","kind":"arxiv","version":2},"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/2407.04603/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":"2026-07-05T09:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lM7NT9zc3yVAKaMS5COzganw7V3aj5+7fbCHBrtTfNeJOdysF1R/M0REZyCsvPR2tloPr8uJ2ysw829QoF+fCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:04:15.021589Z"},"content_sha256":"d5342c8246d02d735dd715a2224ecb5bd6eb5140c769c3de20e63b7f4c341ea4","schema_version":"1.0","event_id":"sha256:d5342c8246d02d735dd715a2224ecb5bd6eb5140c769c3de20e63b7f4c341ea4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTED72D2BSWSHOMSVKHTOSJO3C/bundle.json","state_url":"https://pith.science/pith/KTED72D2BSWSHOMSVKHTOSJO3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTED72D2BSWSHOMSVKHTOSJO3C/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":"2026-08-11T10:04:15Z","links":{"resolver":"https://pith.science/pith/KTED72D2BSWSHOMSVKHTOSJO3C","bundle":"https://pith.science/pith/KTED72D2BSWSHOMSVKHTOSJO3C/bundle.json","state":"https://pith.science/pith/KTED72D2BSWSHOMSVKHTOSJO3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTED72D2BSWSHOMSVKHTOSJO3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KTED72D2BSWSHOMSVKHTOSJO3C","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":"959f9a22694fb09305c2ca5dd6a67f2bdc6176ee556828f0f6fd32f793db4adc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T15:52:23Z","title_canon_sha256":"9920b835ca383afac2800bc38f19bd785cad1f914463ab756d746c212fbd892a"},"schema_version":"1.0","source":{"id":"2407.04603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04603","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04603v2","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04603","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"KTED72D2BSWS","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"KTED72D2BSWSHOMS","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"KTED72D2","created_at":"2026-07-05T09:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:d5342c8246d02d735dd715a2224ecb5bd6eb5140c769c3de20e63b7f4c341ea4","target":"graph","created_at":"2026-07-05T09:16:19Z","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/2407.04603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks. However, we often fail to fully unleash their potential when adapting them for new concept understanding due to limited information on new classes. To address this limitation, we introduce a novel adaptation framework, AWT (Augment, Weight, then Transport). AWT comprises three key components: augmenting inputs with diverse visual perspectives and enriched class descriptions through image transformations and language models; dynamically weighting inputs based on the prediction entropy","authors_text":"Gangshan Wu, Limin Wang, Yuhan Zhu, Yuyang Ji, Zhiyu Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T15:52:23Z","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04603","kind":"arxiv","version":2},"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":"sha256:04cd22e2234a67104ba43027fa985ad09fcaed443007e7be9a9a2a238921f046","target":"record","created_at":"2026-07-05T09:16:19Z","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":"959f9a22694fb09305c2ca5dd6a67f2bdc6176ee556828f0f6fd32f793db4adc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T15:52:23Z","title_canon_sha256":"9920b835ca383afac2800bc38f19bd785cad1f914463ab756d746c212fbd892a"},"schema_version":"1.0","source":{"id":"2407.04603","kind":"arxiv","version":2}},"canonical_sha256":"54c83fe87a0cad23b992aa8f37492ed89ecd453ca93e56ddac9eb674f8e47c62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54c83fe87a0cad23b992aa8f37492ed89ecd453ca93e56ddac9eb674f8e47c62","first_computed_at":"2026-07-05T09:16:19.427163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:19.427163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aKQswUfLlrnKbMElpHZxZNNkjrtHQVK+0bWY4Clcqq63ScMujEUB8p0W+/ifnXh5FVfdjje0V/JB7Va322JSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:19.427770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04cd22e2234a67104ba43027fa985ad09fcaed443007e7be9a9a2a238921f046","sha256:d5342c8246d02d735dd715a2224ecb5bd6eb5140c769c3de20e63b7f4c341ea4"],"state_sha256":"0b0595846d82b854b3cd76140d284d4312f14b9c22e3c61e7a87b228f2ff665c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Lcuget3Nhxaz3iDjOaILjnsGdSYkbjiid1bukiAR0+dH3DG81sauDQi7DMzd5DsqvZa9OBcrhVuoJgaXkPjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:04:15.028618Z","bundle_sha256":"703333031df2f87fa051a63324f6aee6bb56bbad8975c2c10232c2692d494d59"}}