{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IDYPNKACMFHUVGDYP6QNGE4I3V","short_pith_number":"pith:IDYPNKAC","canonical_record":{"source":{"id":"2407.01490","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:26:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2808b75ac2222dedf75f62c94db7d14e62a2931e348cc7b10a6ca6d6d3876b12","abstract_canon_sha256":"afccd19d58c735d5223d78bac926708d5d7d7536eb1e4c3e394d22ed4429ba4e"},"schema_version":"1.0"},"canonical_sha256":"40f0f6a802614f4a98787fa0d31388dd6aa9c74cb5f044a6bb3139aef1df6ce8","source":{"kind":"arxiv","id":"2407.01490","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01490","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01490v2","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01490","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"IDYPNKACMFHU","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_16","alias_value":"IDYPNKACMFHUVGDY","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_8","alias_value":"IDYPNKAC","created_at":"2026-07-05T08:45:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IDYPNKACMFHUVGDYP6QNGE4I3V","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01490","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:26:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2808b75ac2222dedf75f62c94db7d14e62a2931e348cc7b10a6ca6d6d3876b12","abstract_canon_sha256":"afccd19d58c735d5223d78bac926708d5d7d7536eb1e4c3e394d22ed4429ba4e"},"schema_version":"1.0"},"canonical_sha256":"40f0f6a802614f4a98787fa0d31388dd6aa9c74cb5f044a6bb3139aef1df6ce8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:52.188371Z","signature_b64":"bFvH73pUyBkHfpWyNK/zB/SbiMtcE6q7efyw0qz1lyZXG0ZgFbzLvEjezhETEtHNKGUuE91tbcqI4be2dD8ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f0f6a802614f4a98787fa0d31388dd6aa9c74cb5f044a6bb3139aef1df6ce8","last_reissued_at":"2026-07-05T08:45:52.187968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:52.187968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01490","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":"2026-07-05T08:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwRSWOjAvPiK12OXe3DVoe0awfH9G+lKT+vlBi2cUcv+tOc9mEv19RFWBRN8/HPYm8p4ZTPrVwX5fR0EUu33Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:58:56.842391Z"},"content_sha256":"983518084c1fbc90fab92ee3c34ad8944e44d9a63fa436a76e1aeb9efd1d6388","schema_version":"1.0","event_id":"sha256:983518084c1fbc90fab92ee3c34ad8944e44d9a63fa436a76e1aeb9efd1d6388"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IDYPNKACMFHUVGDYP6QNGE4I3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Julia Kreutzer, Lu\\'isa Shimabucoro, Marzieh Fadaee, Sara Hooker, Sebastian Ruder","submitted_at":"2024-07-01T17:26:21Z","abstract_excerpt":"The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive inheritance of model properties by systematically studying the consequences of synthetic data integration. We provide one of the most comprehensive studies to-date of how the source of synthetic data shapes models' internal biases, calibration and generations' textual attributes and preferences. We find that models are surprisingly sensitive towards certain att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01490","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/2407.01490/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":"2026-07-05T08:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYlAu9mhTh/GmsENvqrchMqYJJgwLkv5GiYNY+jI7AXai6GRqlgYzq52UMtfSoBOc8UwHQdwwPWOI9ai8SnsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:58:56.843295Z"},"content_sha256":"cc82184b57dbefe01538825482a857e3f7333d14723fd311f3ba9e367c61f54d","schema_version":"1.0","event_id":"sha256:cc82184b57dbefe01538825482a857e3f7333d14723fd311f3ba9e367c61f54d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/bundle.json","state_url":"https://pith.science/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/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":"2026-08-04T06:58:56Z","links":{"resolver":"https://pith.science/pith/IDYPNKACMFHUVGDYP6QNGE4I3V","bundle":"https://pith.science/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/bundle.json","state":"https://pith.science/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDYPNKACMFHUVGDYP6QNGE4I3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IDYPNKACMFHUVGDYP6QNGE4I3V","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":"afccd19d58c735d5223d78bac926708d5d7d7536eb1e4c3e394d22ed4429ba4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:26:21Z","title_canon_sha256":"2808b75ac2222dedf75f62c94db7d14e62a2931e348cc7b10a6ca6d6d3876b12"},"schema_version":"1.0","source":{"id":"2407.01490","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01490","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01490v2","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01490","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"IDYPNKACMFHU","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_16","alias_value":"IDYPNKACMFHUVGDY","created_at":"2026-07-05T08:45:52Z"},{"alias_kind":"pith_short_8","alias_value":"IDYPNKAC","created_at":"2026-07-05T08:45:52Z"}],"graph_snapshots":[{"event_id":"sha256:cc82184b57dbefe01538825482a857e3f7333d14723fd311f3ba9e367c61f54d","target":"graph","created_at":"2026-07-05T08:45:52Z","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/2407.01490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive inheritance of model properties by systematically studying the consequences of synthetic data integration. We provide one of the most comprehensive studies to-date of how the source of synthetic data shapes models' internal biases, calibration and generations' textual attributes and preferences. We find that models are surprisingly sensitive towards certain att","authors_text":"Julia Kreutzer, Lu\\'isa Shimabucoro, Marzieh Fadaee, Sara Hooker, Sebastian Ruder","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:26:21Z","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01490","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":"sha256:983518084c1fbc90fab92ee3c34ad8944e44d9a63fa436a76e1aeb9efd1d6388","target":"record","created_at":"2026-07-05T08:45:52Z","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":"afccd19d58c735d5223d78bac926708d5d7d7536eb1e4c3e394d22ed4429ba4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:26:21Z","title_canon_sha256":"2808b75ac2222dedf75f62c94db7d14e62a2931e348cc7b10a6ca6d6d3876b12"},"schema_version":"1.0","source":{"id":"2407.01490","kind":"arxiv","version":2}},"canonical_sha256":"40f0f6a802614f4a98787fa0d31388dd6aa9c74cb5f044a6bb3139aef1df6ce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40f0f6a802614f4a98787fa0d31388dd6aa9c74cb5f044a6bb3139aef1df6ce8","first_computed_at":"2026-07-05T08:45:52.187968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:52.187968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bFvH73pUyBkHfpWyNK/zB/SbiMtcE6q7efyw0qz1lyZXG0ZgFbzLvEjezhETEtHNKGUuE91tbcqI4be2dD8ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:52.188371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01490","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:983518084c1fbc90fab92ee3c34ad8944e44d9a63fa436a76e1aeb9efd1d6388","sha256:cc82184b57dbefe01538825482a857e3f7333d14723fd311f3ba9e367c61f54d"],"state_sha256":"3db8fc838337d3106d754385b63c8161a3eabb7ebe13dbe6106ba1d15e833252"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83EYcDawtttHk88+A4aXnY4Mx4NtkqdlxV68TiRzsO9FeG12B0apnccUnysx85vBtNc54To4w8vZkrQlYeYKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:58:56.849800Z","bundle_sha256":"bc5d2f484f1ff0727b973af02e3a59f0a4a3e126c131f50ce4d180e975620f3a"}}