{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LOHBLHC3YRP3NWZBVAFLI7E2PY","short_pith_number":"pith:LOHBLHC3","canonical_record":{"source":{"id":"2409.08239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T17:39:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1239c32194d6658eb941c46268058b034206aca1ccb3db46308923c7920cb7d","abstract_canon_sha256":"966256d91a6982edc6293de57c7486da3785de7fa07b813a83ed775188ac32a1"},"schema_version":"1.0"},"canonical_sha256":"5b8e159c5bc45fb6db21a80ab47c9a7e17740663c81ae327d6053a753f363bdb","source":{"kind":"arxiv","id":"2409.08239","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08239","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08239v2","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08239","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"LOHBLHC3YRP3","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_16","alias_value":"LOHBLHC3YRP3NWZB","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_8","alias_value":"LOHBLHC3","created_at":"2026-07-05T11:56:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LOHBLHC3YRP3NWZBVAFLI7E2PY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T17:39:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1239c32194d6658eb941c46268058b034206aca1ccb3db46308923c7920cb7d","abstract_canon_sha256":"966256d91a6982edc6293de57c7486da3785de7fa07b813a83ed775188ac32a1"},"schema_version":"1.0"},"canonical_sha256":"5b8e159c5bc45fb6db21a80ab47c9a7e17740663c81ae327d6053a753f363bdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:43.112341Z","signature_b64":"guYDElf91H1B6rSB9UpBkTSznepSQnRH+BipiQHYe8FDnLAl0g5T6My6jnqAjKxxFkqOsVNkx41TN4EMEMc+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8e159c5bc45fb6db21a80ab47c9a7e17740663c81ae327d6053a753f363bdb","last_reissued_at":"2026-07-05T11:56:43.111851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:43.111851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08239","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":"2026-07-05T11:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGCxeCSAUMfFDIdOzCsFYuzlQnAntV1GHcm0DF31kkbTAFMZX/A5QQQJ0S28XqKBIRgd02LAFqWO6HSU6gdUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:28:08.651418Z"},"content_sha256":"da6f0c6be7137b61d3588b7b35c764d3640eb43dca636ec3f41dfd2bd0648b6d","schema_version":"1.0","event_id":"sha256:da6f0c6be7137b61d3588b7b35c764d3640eb43dca636ec3f41dfd2bd0648b6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LOHBLHC3YRP3NWZBVAFLI7E2PY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alisia Lupidi, Carlos Gemmell, Jakob Foerster, Jane Dwivedi-Yu, Jason Weston, Maria Lomeli, Nicola Cancedda, Roberta Raileanu","submitted_at":"2024-09-12T17:39:08Z","abstract_excerpt":"Synthetic data generation has recently emerged as a promising approach for enhancing the capabilities of large language models (LLMs) without the need for expensive human annotations. However, existing methods often generate data that can be low quality or contrived. In this paper, we introduce Source2Synth, a scalable approach for synthetic data generation and curation that is grounded in real-world data sources. Source2Synth takes as input a custom data source and produces synthetic data examples with intermediate reasoning steps. Our method improves the dataset quality by discarding low-qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08239","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/2409.08239/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":"2026-07-05T11:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSAtvksQvDuo6YCcpkq4midkwkmW0W/gd4aGSUNeTAFJGcY/ltJvUts0McxYqdOjD4md5UFmL91GeqBekS7ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:28:08.651913Z"},"content_sha256":"d359100d071c54b1029aee42cb2fe62da1cca2064395c9a9be9f020f7c6e30f1","schema_version":"1.0","event_id":"sha256:d359100d071c54b1029aee42cb2fe62da1cca2064395c9a9be9f020f7c6e30f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/bundle.json","state_url":"https://pith.science/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/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":"2026-08-20T19:28:08Z","links":{"resolver":"https://pith.science/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY","bundle":"https://pith.science/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/bundle.json","state":"https://pith.science/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOHBLHC3YRP3NWZBVAFLI7E2PY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LOHBLHC3YRP3NWZBVAFLI7E2PY","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":"966256d91a6982edc6293de57c7486da3785de7fa07b813a83ed775188ac32a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T17:39:08Z","title_canon_sha256":"c1239c32194d6658eb941c46268058b034206aca1ccb3db46308923c7920cb7d"},"schema_version":"1.0","source":{"id":"2409.08239","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08239","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08239v2","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08239","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"LOHBLHC3YRP3","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_16","alias_value":"LOHBLHC3YRP3NWZB","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_8","alias_value":"LOHBLHC3","created_at":"2026-07-05T11:56:43Z"}],"graph_snapshots":[{"event_id":"sha256:d359100d071c54b1029aee42cb2fe62da1cca2064395c9a9be9f020f7c6e30f1","target":"graph","created_at":"2026-07-05T11:56:43Z","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/2409.08239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data generation has recently emerged as a promising approach for enhancing the capabilities of large language models (LLMs) without the need for expensive human annotations. However, existing methods often generate data that can be low quality or contrived. In this paper, we introduce Source2Synth, a scalable approach for synthetic data generation and curation that is grounded in real-world data sources. Source2Synth takes as input a custom data source and produces synthetic data examples with intermediate reasoning steps. Our method improves the dataset quality by discarding low-qua","authors_text":"Alisia Lupidi, Carlos Gemmell, Jakob Foerster, Jane Dwivedi-Yu, Jason Weston, Maria Lomeli, Nicola Cancedda, Roberta Raileanu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T17:39:08Z","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08239","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:da6f0c6be7137b61d3588b7b35c764d3640eb43dca636ec3f41dfd2bd0648b6d","target":"record","created_at":"2026-07-05T11:56:43Z","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":"966256d91a6982edc6293de57c7486da3785de7fa07b813a83ed775188ac32a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T17:39:08Z","title_canon_sha256":"c1239c32194d6658eb941c46268058b034206aca1ccb3db46308923c7920cb7d"},"schema_version":"1.0","source":{"id":"2409.08239","kind":"arxiv","version":2}},"canonical_sha256":"5b8e159c5bc45fb6db21a80ab47c9a7e17740663c81ae327d6053a753f363bdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b8e159c5bc45fb6db21a80ab47c9a7e17740663c81ae327d6053a753f363bdb","first_computed_at":"2026-07-05T11:56:43.111851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:43.111851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"guYDElf91H1B6rSB9UpBkTSznepSQnRH+BipiQHYe8FDnLAl0g5T6My6jnqAjKxxFkqOsVNkx41TN4EMEMc+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:43.112341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08239","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da6f0c6be7137b61d3588b7b35c764d3640eb43dca636ec3f41dfd2bd0648b6d","sha256:d359100d071c54b1029aee42cb2fe62da1cca2064395c9a9be9f020f7c6e30f1"],"state_sha256":"b9cefb0a8bf5060df8ec94417e186c835e1f8856a87cc0b91d45af415ce6c28f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmvihE0yxlmVCiI3GmnI80UTb6XwTymcSGJvc0hDB/OgQ390D9w6/6+//aYAePZRWMJE0LaVWIPf/bDf4GGiAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T19:28:08.656396Z","bundle_sha256":"551fe80afd13bd000deabc9958bf9efedf6f49e7ef17a7c4c217dd92128f1d05"}}