{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ICUNQHOTV2A2NJPDO744CJ2T4I","short_pith_number":"pith:ICUNQHOT","canonical_record":{"source":{"id":"2409.07431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T17:21:59Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"c99c16dd4f7e777b0fe2bd85c7aaacf66d24e58c9c8e8bc0d341b0be37f98959","abstract_canon_sha256":"f672d8560a494efddfeed06c3010fceac91edd21ea763f5643b18c730ba05400"},"schema_version":"1.0"},"canonical_sha256":"40a8d81dd3ae81a6a5e377f9c12753e2287d1f14837a9724e9243b388098574e","source":{"kind":"arxiv","id":"2409.07431","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07431","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07431v2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07431","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"ICUNQHOTV2A2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"ICUNQHOTV2A2NJPD","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"ICUNQHOT","created_at":"2026-07-05T09:15:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ICUNQHOTV2A2NJPDO744CJ2T4I","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T17:21:59Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"c99c16dd4f7e777b0fe2bd85c7aaacf66d24e58c9c8e8bc0d341b0be37f98959","abstract_canon_sha256":"f672d8560a494efddfeed06c3010fceac91edd21ea763f5643b18c730ba05400"},"schema_version":"1.0"},"canonical_sha256":"40a8d81dd3ae81a6a5e377f9c12753e2287d1f14837a9724e9243b388098574e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:14.417148Z","signature_b64":"3Ek5+EsB1imUt7UrBBzt4DT5yFE1ttTxn6Gk/wmN4hISZNv7cPyjKxH5jp/Kc7SUA09RrlU894S2clH2kmsPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a8d81dd3ae81a6a5e377f9c12753e2287d1f14837a9724e9243b388098574e","last_reissued_at":"2026-07-05T09:15:14.416683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:14.416683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07431","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":"2026-07-05T09:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6BQqsnuTnwz0KYXdxpXc6nsumlr5xKDFDBqmRcdgkfCC1AIjQJdySypMofV8mt+ZQ/Y8qCl2/3hVipO6HALCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:46.785172Z"},"content_sha256":"00d280e9926dd21f8cf14cccaed5f6a9d475625b6c972c0a1c297a8ddcb1d801","schema_version":"1.0","event_id":"sha256:00d280e9926dd21f8cf14cccaed5f6a9d475625b6c972c0a1c297a8ddcb1d801"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ICUNQHOTV2A2NJPDO744CJ2T4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic continued pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emmanuel Cand\\`es, Neil Band, Shuangping Li, Tatsunori Hashimoto, Zitong Yang","submitted_at":"2024-09-11T17:21:59Z","abstract_excerpt":"Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge. However, this knowledge acquisition is data-inefficient--to learn a given fact, models must be trained on hundreds to thousands of diverse representations of it. This poses a challenge when adapting a pretrained model to a small corpus of domain-specific documents, where each fact may appear rarely or only once. We propose to bridge this gap with synthetic continued pretraining: using the small domain-specific corpus to synthesize a large corpus more amenable to le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07431","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/2409.07431/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":"2026-07-05T09:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYqOxKQMiBACIK0uEfaD4TxMGYYsrg2fhkdMBBeiSj58oups3wmA/e+4V9eKP3kx3I+M+pzagQH+l4I3ZxPABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:46.785688Z"},"content_sha256":"645384d05a54bf06e90b7b5ba8507582e0062e18996483d558ffd2b900ee9df1","schema_version":"1.0","event_id":"sha256:645384d05a54bf06e90b7b5ba8507582e0062e18996483d558ffd2b900ee9df1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/bundle.json","state_url":"https://pith.science/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/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":"2026-08-08T17:01:46Z","links":{"resolver":"https://pith.science/pith/ICUNQHOTV2A2NJPDO744CJ2T4I","bundle":"https://pith.science/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/bundle.json","state":"https://pith.science/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICUNQHOTV2A2NJPDO744CJ2T4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICUNQHOTV2A2NJPDO744CJ2T4I","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":"f672d8560a494efddfeed06c3010fceac91edd21ea763f5643b18c730ba05400","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T17:21:59Z","title_canon_sha256":"c99c16dd4f7e777b0fe2bd85c7aaacf66d24e58c9c8e8bc0d341b0be37f98959"},"schema_version":"1.0","source":{"id":"2409.07431","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07431","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07431v2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07431","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"ICUNQHOTV2A2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"ICUNQHOTV2A2NJPD","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"ICUNQHOT","created_at":"2026-07-05T09:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:645384d05a54bf06e90b7b5ba8507582e0062e18996483d558ffd2b900ee9df1","target":"graph","created_at":"2026-07-05T09:15:14Z","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/2409.07431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge. However, this knowledge acquisition is data-inefficient--to learn a given fact, models must be trained on hundreds to thousands of diverse representations of it. This poses a challenge when adapting a pretrained model to a small corpus of domain-specific documents, where each fact may appear rarely or only once. We propose to bridge this gap with synthetic continued pretraining: using the small domain-specific corpus to synthesize a large corpus more amenable to le","authors_text":"Emmanuel Cand\\`es, Neil Band, Shuangping Li, Tatsunori Hashimoto, Zitong Yang","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T17:21:59Z","title":"Synthetic continued pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07431","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":"sha256:00d280e9926dd21f8cf14cccaed5f6a9d475625b6c972c0a1c297a8ddcb1d801","target":"record","created_at":"2026-07-05T09:15:14Z","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":"f672d8560a494efddfeed06c3010fceac91edd21ea763f5643b18c730ba05400","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T17:21:59Z","title_canon_sha256":"c99c16dd4f7e777b0fe2bd85c7aaacf66d24e58c9c8e8bc0d341b0be37f98959"},"schema_version":"1.0","source":{"id":"2409.07431","kind":"arxiv","version":2}},"canonical_sha256":"40a8d81dd3ae81a6a5e377f9c12753e2287d1f14837a9724e9243b388098574e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40a8d81dd3ae81a6a5e377f9c12753e2287d1f14837a9724e9243b388098574e","first_computed_at":"2026-07-05T09:15:14.416683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:14.416683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Ek5+EsB1imUt7UrBBzt4DT5yFE1ttTxn6Gk/wmN4hISZNv7cPyjKxH5jp/Kc7SUA09RrlU894S2clH2kmsPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:14.417148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07431","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00d280e9926dd21f8cf14cccaed5f6a9d475625b6c972c0a1c297a8ddcb1d801","sha256:645384d05a54bf06e90b7b5ba8507582e0062e18996483d558ffd2b900ee9df1"],"state_sha256":"7b593119ef12eb3a4622413ded75d07d88fe2ec76f4c5754f9a6cebd2d484157"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JKU6EvzADZJYIemwZj+DvvESmUf4C8yDhNYkS4lo7b9g63bGzo41kwuzC+cuPcg1LEzeMRo7ePuJpFwG6M04Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:01:46.791096Z","bundle_sha256":"d379ebda451b2ce779e7998027611edabcc109bfe947224bd40ae710dffdb8b0"}}