{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PLAAADVOTDI4J4JPFH46LXNNUF","short_pith_number":"pith:PLAAADVO","canonical_record":{"source":{"id":"2505.23031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:18:25Z","cross_cats_sorted":[],"title_canon_sha256":"95697a232cc26bd37b00a132398a14ac0d534d698daa1d2f185d918bf0049840","abstract_canon_sha256":"e71be550a2df10372a52cc07815c564390a1aaba4bccf5280ed4fd3a73851342"},"schema_version":"1.0"},"canonical_sha256":"7ac0000eae98d1c4f12f29f9e5ddada16ee1d96826f370e9dd55dd301e8f474f","source":{"kind":"arxiv","id":"2505.23031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23031","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23031v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23031","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"PLAAADVOTDI4","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"PLAAADVOTDI4J4JP","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"PLAAADVO","created_at":"2026-07-05T11:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PLAAADVOTDI4J4JPFH46LXNNUF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:18:25Z","cross_cats_sorted":[],"title_canon_sha256":"95697a232cc26bd37b00a132398a14ac0d534d698daa1d2f185d918bf0049840","abstract_canon_sha256":"e71be550a2df10372a52cc07815c564390a1aaba4bccf5280ed4fd3a73851342"},"schema_version":"1.0"},"canonical_sha256":"7ac0000eae98d1c4f12f29f9e5ddada16ee1d96826f370e9dd55dd301e8f474f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.918380Z","signature_b64":"y26EzEBStY6KRuxp5Sh2lW+7791lB0F8xnXT0cZJaQZsxjAc/IE8bzjc2tA3lr3ySvabrNS7LGgbLxiPIKehCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ac0000eae98d1c4f12f29f9e5ddada16ee1d96826f370e9dd55dd301e8f474f","last_reissued_at":"2026-07-05T11:11:53.917821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.917821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23031","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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bAhRr1BqVPU4NX1tVhNuSB+QrVs1QPxVF7PwFYGQBywJm81pr5xLPMh687Zn5rZbUIifuUU7LAnyWWpgOz2XDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:16:07.279924Z"},"content_sha256":"362708983ff50a9a2d33346cd52e937e15c7a6292c3bc489316c78ca75764cbb","schema_version":"1.0","event_id":"sha256:362708983ff50a9a2d33346cd52e937e15c7a6292c3bc489316c78ca75764cbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PLAAADVOTDI4J4JPFH46LXNNUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyao Yu, Dongliang Chang, Jinyi Chang, Lei Chen, Zhanyu Ma","submitted_at":"2025-05-29T03:18:25Z","abstract_excerpt":"In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level labels, making them impractical in privacy-sensitive scenarios such as medical image analysis. This paper aims to enable accurate fine-grained recognition without direct access to instance labels. To achieve this, we leverage the Learning from Label Proportions (LLP) paradigm, which requires only bag-level labels for efficient training. Unlike existing LLP-based methods, our framework explicitly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23031","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/2505.23031/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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+BoMKs+awaKEJnxDfhfVShcNIE5+9cIv5nXU0gnT2Fc3vG2rs/97O7TqRuGOq220DogyskaODHykcSVT1/8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:16:07.280866Z"},"content_sha256":"91af8c2e18273bba1ea58f8174e1f6e2ea3cc3c8dae36e69e9a09703a8b149ce","schema_version":"1.0","event_id":"sha256:91af8c2e18273bba1ea58f8174e1f6e2ea3cc3c8dae36e69e9a09703a8b149ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLAAADVOTDI4J4JPFH46LXNNUF/bundle.json","state_url":"https://pith.science/pith/PLAAADVOTDI4J4JPFH46LXNNUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLAAADVOTDI4J4JPFH46LXNNUF/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":"2026-08-08T12:16:07Z","links":{"resolver":"https://pith.science/pith/PLAAADVOTDI4J4JPFH46LXNNUF","bundle":"https://pith.science/pith/PLAAADVOTDI4J4JPFH46LXNNUF/bundle.json","state":"https://pith.science/pith/PLAAADVOTDI4J4JPFH46LXNNUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLAAADVOTDI4J4JPFH46LXNNUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PLAAADVOTDI4J4JPFH46LXNNUF","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":"e71be550a2df10372a52cc07815c564390a1aaba4bccf5280ed4fd3a73851342","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:18:25Z","title_canon_sha256":"95697a232cc26bd37b00a132398a14ac0d534d698daa1d2f185d918bf0049840"},"schema_version":"1.0","source":{"id":"2505.23031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23031","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23031v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23031","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"PLAAADVOTDI4","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"PLAAADVOTDI4J4JP","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"PLAAADVO","created_at":"2026-07-05T11:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:91af8c2e18273bba1ea58f8174e1f6e2ea3cc3c8dae36e69e9a09703a8b149ce","target":"graph","created_at":"2026-07-05T11:11:53Z","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/2505.23031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level labels, making them impractical in privacy-sensitive scenarios such as medical image analysis. This paper aims to enable accurate fine-grained recognition without direct access to instance labels. To achieve this, we leverage the Learning from Label Proportions (LLP) paradigm, which requires only bag-level labels for efficient training. Unlike existing LLP-based methods, our framework explicitly","authors_text":"Bingyao Yu, Dongliang Chang, Jinyi Chang, Lei Chen, Zhanyu Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:18:25Z","title":"Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23031","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":"sha256:362708983ff50a9a2d33346cd52e937e15c7a6292c3bc489316c78ca75764cbb","target":"record","created_at":"2026-07-05T11:11:53Z","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":"e71be550a2df10372a52cc07815c564390a1aaba4bccf5280ed4fd3a73851342","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:18:25Z","title_canon_sha256":"95697a232cc26bd37b00a132398a14ac0d534d698daa1d2f185d918bf0049840"},"schema_version":"1.0","source":{"id":"2505.23031","kind":"arxiv","version":1}},"canonical_sha256":"7ac0000eae98d1c4f12f29f9e5ddada16ee1d96826f370e9dd55dd301e8f474f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ac0000eae98d1c4f12f29f9e5ddada16ee1d96826f370e9dd55dd301e8f474f","first_computed_at":"2026-07-05T11:11:53.917821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:53.917821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y26EzEBStY6KRuxp5Sh2lW+7791lB0F8xnXT0cZJaQZsxjAc/IE8bzjc2tA3lr3ySvabrNS7LGgbLxiPIKehCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:53.918380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:362708983ff50a9a2d33346cd52e937e15c7a6292c3bc489316c78ca75764cbb","sha256:91af8c2e18273bba1ea58f8174e1f6e2ea3cc3c8dae36e69e9a09703a8b149ce"],"state_sha256":"e862ad85595785f4b512beec6b5fc9d61d9db2350d5179d1a0020662bf45c1eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J5VZ6C2s8hTk3xA42LOmfnmXw03x8V61J1xrb02jl3b7DiQiZG4XIzlHhwcap8lQ30PLqb5KFx6jrIobhxpyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:16:07.289230Z","bundle_sha256":"a71648981f330464c5d51ead79c7c1807dff5c673fa9fb9343521187e053290a"}}