{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WUX3DHS372WY4LMVJ27HOPRASH","short_pith_number":"pith:WUX3DHS3","canonical_record":{"source":{"id":"2406.20085","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"572ae9266614b47dd0be8230d152dc9986cd8a138ec1de642ace23882c77d14f","abstract_canon_sha256":"459542814fa624fbcb1eab64ebf195e7e9c92e5e5e86dfb06038ba0c04b50b86"},"schema_version":"1.0"},"canonical_sha256":"b52fb19e5bfead8e2d954ebe773e2091f35660971be10bb0e553b6e9c27092ae","source":{"kind":"arxiv","id":"2406.20085","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20085","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20085v3","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20085","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUX3DHS372WY","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUX3DHS372WY4LMV","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUX3DHS3","created_at":"2026-07-05T10:37:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WUX3DHS372WY4LMVJ27HOPRASH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.20085","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"572ae9266614b47dd0be8230d152dc9986cd8a138ec1de642ace23882c77d14f","abstract_canon_sha256":"459542814fa624fbcb1eab64ebf195e7e9c92e5e5e86dfb06038ba0c04b50b86"},"schema_version":"1.0"},"canonical_sha256":"b52fb19e5bfead8e2d954ebe773e2091f35660971be10bb0e553b6e9c27092ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:28.172854Z","signature_b64":"XDiuWc4+NJTA98S8YO04GM6ytOJfhdP17wiRUpqGujY/HXwTIFtM/47O4/n7SFnKwBMAoo0thq5/nWnJ/DpyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b52fb19e5bfead8e2d954ebe773e2091f35660971be10bb0e553b6e9c27092ae","last_reissued_at":"2026-07-05T10:37:28.172364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:28.172364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.20085","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CXVscLBH1k65w5N4VYHMNat/oT+aZ2J30UwScXuFQLvKlrKA7a8b+qPyipEDlWTHcxwVzg1y/KW5mdrf5DuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:14.490132Z"},"content_sha256":"e41e238e1875b2c02a040726bd536e24045b4bb4f4e3ea67bb5d5ba5eea5d8d0","schema_version":"1.0","event_id":"sha256:e41e238e1875b2c02a040726bd536e24045b4bb4f4e3ea67bb5d5ba5eea5d8d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WUX3DHS372WY4LMVJ27HOPRASH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzong Wu, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yanhong Zeng, Yicheng Chen, Yining Li","submitted_at":"2024-06-28T17:53:18Z","abstract_excerpt":"Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boost performance on downstream tasks with synthetic data poses several challenges, including aligning with real data distribution, scaling synthetic sample volumes, and ensuring their quality. To bridge these gaps, we present \\textbf{A}uto \\textbf{C}herry-\\textbf{P}icker (ACP), a novel framework that generates high-quality cross-modality training samples at scale to augment perception and multi-modal training. ACP first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20085","kind":"arxiv","version":3},"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/2406.20085/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":"2026-07-05T10:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCVruOw8GgQvRhEVZoZ361TG+42CtqTMYWy40rNoi6XzDjNo76J4FwF58dTt9mM0bZbK2nqUd11xIS6YQah4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:14.490634Z"},"content_sha256":"4ac30480be76e3749242a0962da5e0f97fe51f1e6ca176a2362d3c8a033bcda8","schema_version":"1.0","event_id":"sha256:4ac30480be76e3749242a0962da5e0f97fe51f1e6ca176a2362d3c8a033bcda8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUX3DHS372WY4LMVJ27HOPRASH/bundle.json","state_url":"https://pith.science/pith/WUX3DHS372WY4LMVJ27HOPRASH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUX3DHS372WY4LMVJ27HOPRASH/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":"2026-08-05T20:14:14Z","links":{"resolver":"https://pith.science/pith/WUX3DHS372WY4LMVJ27HOPRASH","bundle":"https://pith.science/pith/WUX3DHS372WY4LMVJ27HOPRASH/bundle.json","state":"https://pith.science/pith/WUX3DHS372WY4LMVJ27HOPRASH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUX3DHS372WY4LMVJ27HOPRASH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WUX3DHS372WY4LMVJ27HOPRASH","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":"459542814fa624fbcb1eab64ebf195e7e9c92e5e5e86dfb06038ba0c04b50b86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:53:18Z","title_canon_sha256":"572ae9266614b47dd0be8230d152dc9986cd8a138ec1de642ace23882c77d14f"},"schema_version":"1.0","source":{"id":"2406.20085","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20085","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20085v3","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20085","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUX3DHS372WY","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUX3DHS372WY4LMV","created_at":"2026-07-05T10:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUX3DHS3","created_at":"2026-07-05T10:37:28Z"}],"graph_snapshots":[{"event_id":"sha256:4ac30480be76e3749242a0962da5e0f97fe51f1e6ca176a2362d3c8a033bcda8","target":"graph","created_at":"2026-07-05T10:37:28Z","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/2406.20085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boost performance on downstream tasks with synthetic data poses several challenges, including aligning with real data distribution, scaling synthetic sample volumes, and ensuring their quality. To bridge these gaps, we present \\textbf{A}uto \\textbf{C}herry-\\textbf{P}icker (ACP), a novel framework that generates high-quality cross-modality training samples at scale to augment perception and multi-modal training. ACP first","authors_text":"Jianzong Wu, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yanhong Zeng, Yicheng Chen, Yining Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:53:18Z","title":"Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20085","kind":"arxiv","version":3},"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:e41e238e1875b2c02a040726bd536e24045b4bb4f4e3ea67bb5d5ba5eea5d8d0","target":"record","created_at":"2026-07-05T10:37:28Z","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":"459542814fa624fbcb1eab64ebf195e7e9c92e5e5e86dfb06038ba0c04b50b86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:53:18Z","title_canon_sha256":"572ae9266614b47dd0be8230d152dc9986cd8a138ec1de642ace23882c77d14f"},"schema_version":"1.0","source":{"id":"2406.20085","kind":"arxiv","version":3}},"canonical_sha256":"b52fb19e5bfead8e2d954ebe773e2091f35660971be10bb0e553b6e9c27092ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b52fb19e5bfead8e2d954ebe773e2091f35660971be10bb0e553b6e9c27092ae","first_computed_at":"2026-07-05T10:37:28.172364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:28.172364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XDiuWc4+NJTA98S8YO04GM6ytOJfhdP17wiRUpqGujY/HXwTIFtM/47O4/n7SFnKwBMAoo0thq5/nWnJ/DpyDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:28.172854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20085","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e41e238e1875b2c02a040726bd536e24045b4bb4f4e3ea67bb5d5ba5eea5d8d0","sha256:4ac30480be76e3749242a0962da5e0f97fe51f1e6ca176a2362d3c8a033bcda8"],"state_sha256":"a8f12b40b5e0e3f23404291121b61d87d9510ed70f39e3d0a10975cfd7b12c9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"De7xsaDpwT8cv9H+WlxUf0ueYvBoEzQcTTg0Q/dNI9V+CiUWkKss42tRy3qpEzsDt+/pRCZPR/0Vo+JM6qH+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:14:14.494151Z","bundle_sha256":"9c9e68907d8a37f941fa896b5a1bb56f0cbac760782f7682852d8ac2409a25a2"}}