{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LIODAA43KT6AHUUXAIMLFAGDBM","short_pith_number":"pith:LIODAA43","canonical_record":{"source":{"id":"2510.24078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-28T05:40:14Z","cross_cats_sorted":[],"title_canon_sha256":"91186d60b77f95c7c04276186aa2b0ea0cffcd81a129fd85fb26243078fb2504","abstract_canon_sha256":"854a9f795bc529cc71392b633d7838c391a68768549375b0d42dc7715b16cf52"},"schema_version":"1.0"},"canonical_sha256":"5a1c30039b54fc03d2970218b280c30b2f0580c08e0fa8d8f2bb8a856b97bf41","source":{"kind":"arxiv","id":"2510.24078","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.24078","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2510.24078v2","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.24078","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"LIODAA43KT6A","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"LIODAA43KT6AHUUX","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"LIODAA43","created_at":"2026-06-02T01:03:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LIODAA43KT6AHUUXAIMLFAGDBM","target":"record","payload":{"canonical_record":{"source":{"id":"2510.24078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-28T05:40:14Z","cross_cats_sorted":[],"title_canon_sha256":"91186d60b77f95c7c04276186aa2b0ea0cffcd81a129fd85fb26243078fb2504","abstract_canon_sha256":"854a9f795bc529cc71392b633d7838c391a68768549375b0d42dc7715b16cf52"},"schema_version":"1.0"},"canonical_sha256":"5a1c30039b54fc03d2970218b280c30b2f0580c08e0fa8d8f2bb8a856b97bf41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:35.692573Z","signature_b64":"CEMLnPhU6RzXES9YMsNgJp1fefPMc/gGlfSZDHUmYPZh5Sdwo4ASTxUYIl/w9XxSY4H7ayAPDgZ7u3hDfoLaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1c30039b54fc03d2970218b280c30b2f0580c08e0fa8d8f2bb8a856b97bf41","last_reissued_at":"2026-06-02T01:03:35.691983Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:35.691983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.24078","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":"2026-06-02T01:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Ebvrq7qUsM7d39Vp4Kprtp+DXDdIgSgb9X9yKbt/SFseNz1AyXJumFV/W0cye4fObf44ZbwqVU30fr04+KiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:27:15.192628Z"},"content_sha256":"16199b34080751ad649be567ab7360556cb5dcea0bbc8cecbbdc5fc504121139","schema_version":"1.0","event_id":"sha256:16199b34080751ad649be567ab7360556cb5dcea0bbc8cecbbdc5fc504121139"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LIODAA43KT6AHUUXAIMLFAGDBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esin Tureci, Olga Russakovsky, William Yang, Xindi Wu, Zhiwei Deng","submitted_at":"2025-10-28T05:40:14Z","abstract_excerpt":"Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve the quality of synthetic training data; however, it may also cause overfitting and reduce diversity in the generated samples. We propose a fine-tuning strategy BOB (BeyondOBjects) to mitigate these concerns for fine-grained classification. Given a small set of real examples, we first extract class-agnostic attributes such as scene background and object pose. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.24078","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/2510.24078/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":"2026-06-02T01:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lvult7Kf/Bw6OUPJbHQhIYIYlgEghW3xJ7AHzni+0ktaKxIZXgcS7jcF5LUmDbqO+0CywT7Tcj8EjxnobSmZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:27:15.193013Z"},"content_sha256":"7d002919687a8b06777092cf5a2e3349d71a0ff41b9876814bd6e70140033735","schema_version":"1.0","event_id":"sha256:7d002919687a8b06777092cf5a2e3349d71a0ff41b9876814bd6e70140033735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIODAA43KT6AHUUXAIMLFAGDBM/bundle.json","state_url":"https://pith.science/pith/LIODAA43KT6AHUUXAIMLFAGDBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIODAA43KT6AHUUXAIMLFAGDBM/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":"2026-06-04T00:27:15Z","links":{"resolver":"https://pith.science/pith/LIODAA43KT6AHUUXAIMLFAGDBM","bundle":"https://pith.science/pith/LIODAA43KT6AHUUXAIMLFAGDBM/bundle.json","state":"https://pith.science/pith/LIODAA43KT6AHUUXAIMLFAGDBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIODAA43KT6AHUUXAIMLFAGDBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LIODAA43KT6AHUUXAIMLFAGDBM","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":"854a9f795bc529cc71392b633d7838c391a68768549375b0d42dc7715b16cf52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-28T05:40:14Z","title_canon_sha256":"91186d60b77f95c7c04276186aa2b0ea0cffcd81a129fd85fb26243078fb2504"},"schema_version":"1.0","source":{"id":"2510.24078","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.24078","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2510.24078v2","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.24078","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"LIODAA43KT6A","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"LIODAA43KT6AHUUX","created_at":"2026-06-02T01:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"LIODAA43","created_at":"2026-06-02T01:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:7d002919687a8b06777092cf5a2e3349d71a0ff41b9876814bd6e70140033735","target":"graph","created_at":"2026-06-02T01:03:35Z","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/2510.24078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve the quality of synthetic training data; however, it may also cause overfitting and reduce diversity in the generated samples. We propose a fine-tuning strategy BOB (BeyondOBjects) to mitigate these concerns for fine-grained classification. Given a small set of real examples, we first extract class-agnostic attributes such as scene background and object pose. W","authors_text":"Esin Tureci, Olga Russakovsky, William Yang, Xindi Wu, Zhiwei Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-28T05:40:14Z","title":"Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.24078","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":"sha256:16199b34080751ad649be567ab7360556cb5dcea0bbc8cecbbdc5fc504121139","target":"record","created_at":"2026-06-02T01:03:35Z","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":"854a9f795bc529cc71392b633d7838c391a68768549375b0d42dc7715b16cf52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-28T05:40:14Z","title_canon_sha256":"91186d60b77f95c7c04276186aa2b0ea0cffcd81a129fd85fb26243078fb2504"},"schema_version":"1.0","source":{"id":"2510.24078","kind":"arxiv","version":2}},"canonical_sha256":"5a1c30039b54fc03d2970218b280c30b2f0580c08e0fa8d8f2bb8a856b97bf41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a1c30039b54fc03d2970218b280c30b2f0580c08e0fa8d8f2bb8a856b97bf41","first_computed_at":"2026-06-02T01:03:35.691983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:35.691983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEMLnPhU6RzXES9YMsNgJp1fefPMc/gGlfSZDHUmYPZh5Sdwo4ASTxUYIl/w9XxSY4H7ayAPDgZ7u3hDfoLaBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:35.692573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.24078","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16199b34080751ad649be567ab7360556cb5dcea0bbc8cecbbdc5fc504121139","sha256:7d002919687a8b06777092cf5a2e3349d71a0ff41b9876814bd6e70140033735"],"state_sha256":"111da47eb4261b7ed105754517af30baf154bbad719b64f2666ef66d6e525003"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d1QpRQx3lZBktbcNGJQClCWzEETOjhxpu69ZcJ5GuS9pSmErZunG1BPy3d2xGal1YXoEJ+/wz44hfraDFa/4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T00:27:15.195004Z","bundle_sha256":"3658dbde67ce0864eef7636a2a14a8dffa693c77bed6103d0016b811929afc15"}}