{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T6JVAGZJ53GE5TF6AN6KGE7HBW","short_pith_number":"pith:T6JVAGZJ","canonical_record":{"source":{"id":"2505.04992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T06:55:22Z","cross_cats_sorted":["cs.LG","stat.AP"],"title_canon_sha256":"154b17ef2e8a822e9d30db387e4174395d22bccc726daba8fe07728a51201a04","abstract_canon_sha256":"99094c6a21cbb9b3e316d4374237bd2c517662adfe4fcf38dd7e2edfddd5c7b4"},"schema_version":"1.0"},"canonical_sha256":"9f93501b29eecc4eccbe037ca313e70dad7b5e006ead89b6582b45c38b9c5def","source":{"kind":"arxiv","id":"2505.04992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04992","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04992v1","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04992","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"T6JVAGZJ53GE","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"T6JVAGZJ53GE5TF6","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"T6JVAGZJ","created_at":"2026-07-05T11:00:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T6JVAGZJ53GE5TF6AN6KGE7HBW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.04992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T06:55:22Z","cross_cats_sorted":["cs.LG","stat.AP"],"title_canon_sha256":"154b17ef2e8a822e9d30db387e4174395d22bccc726daba8fe07728a51201a04","abstract_canon_sha256":"99094c6a21cbb9b3e316d4374237bd2c517662adfe4fcf38dd7e2edfddd5c7b4"},"schema_version":"1.0"},"canonical_sha256":"9f93501b29eecc4eccbe037ca313e70dad7b5e006ead89b6582b45c38b9c5def","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:17.440082Z","signature_b64":"kgOquWSTIv27UDv1i4qjAqKAYZWwYRcE1+y6dA73nEB2nY8lCXt202Rt+pkezAbQ+2IPz8nhQsxd3K5ZbcBuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f93501b29eecc4eccbe037ca313e70dad7b5e006ead89b6582b45c38b9c5def","last_reissued_at":"2026-07-05T11:00:17.439513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:17.439513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.04992","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":"2026-07-05T11:00:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeL1F+5BjfpGx2yB7kIZtox8aFa2DMKKgZ9lnZ6ZUnGbQFnWMrQZa9205/Y+9bX1LqwJXOo1aKvqUN3iA7OCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:21:20.313338Z"},"content_sha256":"275bed9de62e668960bc62a8e797e7cde7893656646d99febba19af93439c443","schema_version":"1.0","event_id":"sha256:275bed9de62e668960bc62a8e797e7cde7893656646d99febba19af93439c443"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T6JVAGZJ53GE5TF6AN6KGE7HBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Statistic Learning with Synthetic Data from Pretrained Large Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Jialong Jiang, Jian Huang, Wenkang Hu, Xu Liu, Yuling Jiao","submitted_at":"2025-05-08T06:55:22Z","abstract_excerpt":"The rapid advancement of generative models, such as Stable Diffusion, raises a key question: how can synthetic data from these models enhance predictive modeling? While they can generate vast amounts of datasets, only a subset meaningfully improves performance. We propose a novel end-to-end framework that generates and systematically filters synthetic data through domain-specific statistical methods, selectively integrating high-quality samples for effective augmentation. Our experiments demonstrate consistent improvements in predictive performance across various settings, highlighting the pot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04992","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/2505.04992/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":"2026-07-05T11:00:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHicFtmQIaHIP0sMGq2/WG6RMBCruY0ZwrFoO0vENsZD4IGOQGt2YLX6UvXoT3iAlNNJleFD5H5dFD6fI5dQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:21:20.313876Z"},"content_sha256":"f6353c25e334169071425f15deb5b08746fe874ca7d3ea3c5abb066cb3999052","schema_version":"1.0","event_id":"sha256:f6353c25e334169071425f15deb5b08746fe874ca7d3ea3c5abb066cb3999052"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/bundle.json","state_url":"https://pith.science/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/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":"2026-08-15T19:21:20Z","links":{"resolver":"https://pith.science/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW","bundle":"https://pith.science/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/bundle.json","state":"https://pith.science/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6JVAGZJ53GE5TF6AN6KGE7HBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T6JVAGZJ53GE5TF6AN6KGE7HBW","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":"99094c6a21cbb9b3e316d4374237bd2c517662adfe4fcf38dd7e2edfddd5c7b4","cross_cats_sorted":["cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T06:55:22Z","title_canon_sha256":"154b17ef2e8a822e9d30db387e4174395d22bccc726daba8fe07728a51201a04"},"schema_version":"1.0","source":{"id":"2505.04992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04992","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04992v1","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04992","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"T6JVAGZJ53GE","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"T6JVAGZJ53GE5TF6","created_at":"2026-07-05T11:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"T6JVAGZJ","created_at":"2026-07-05T11:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:f6353c25e334169071425f15deb5b08746fe874ca7d3ea3c5abb066cb3999052","target":"graph","created_at":"2026-07-05T11:00:17Z","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/2505.04992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of generative models, such as Stable Diffusion, raises a key question: how can synthetic data from these models enhance predictive modeling? While they can generate vast amounts of datasets, only a subset meaningfully improves performance. We propose a novel end-to-end framework that generates and systematically filters synthetic data through domain-specific statistical methods, selectively integrating high-quality samples for effective augmentation. Our experiments demonstrate consistent improvements in predictive performance across various settings, highlighting the pot","authors_text":"Jialong Jiang, Jian Huang, Wenkang Hu, Xu Liu, Yuling Jiao","cross_cats":["cs.LG","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T06:55:22Z","title":"Boosting Statistic Learning with Synthetic Data from Pretrained Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04992","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":"sha256:275bed9de62e668960bc62a8e797e7cde7893656646d99febba19af93439c443","target":"record","created_at":"2026-07-05T11:00:17Z","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":"99094c6a21cbb9b3e316d4374237bd2c517662adfe4fcf38dd7e2edfddd5c7b4","cross_cats_sorted":["cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T06:55:22Z","title_canon_sha256":"154b17ef2e8a822e9d30db387e4174395d22bccc726daba8fe07728a51201a04"},"schema_version":"1.0","source":{"id":"2505.04992","kind":"arxiv","version":1}},"canonical_sha256":"9f93501b29eecc4eccbe037ca313e70dad7b5e006ead89b6582b45c38b9c5def","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f93501b29eecc4eccbe037ca313e70dad7b5e006ead89b6582b45c38b9c5def","first_computed_at":"2026-07-05T11:00:17.439513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:17.439513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgOquWSTIv27UDv1i4qjAqKAYZWwYRcE1+y6dA73nEB2nY8lCXt202Rt+pkezAbQ+2IPz8nhQsxd3K5ZbcBuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:17.440082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:275bed9de62e668960bc62a8e797e7cde7893656646d99febba19af93439c443","sha256:f6353c25e334169071425f15deb5b08746fe874ca7d3ea3c5abb066cb3999052"],"state_sha256":"d426a3040b3672cebc88e78a0465380289707a1ff6e1e2a1f4a6a038fe524a59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUDsA4chXmYj10WSaBrOFMr62Hy+blQ9oxy+sjBvuORXqq4F49qDahnjoZJsQy7USTsYzo9/StFIXUmPkSaZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:21:20.318862Z","bundle_sha256":"62a83ac71db75f608bb5602e63a2c7ec9d5d51441bb61ba6acbf3aa082089d5a"}}