{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RBUMVUJZFC6MEI5BXXNITVK6EN","short_pith_number":"pith:RBUMVUJZ","canonical_record":{"source":{"id":"2508.10975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:55:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f74c929428c052a999fed20deabcfc2400a5b6f41f2848c23d670395516d80d","abstract_canon_sha256":"fb1e6b8a3b1acd3b91ded9cc1f6d638d51a9086203d0f06882e09b9672ac32d1"},"schema_version":"1.0"},"canonical_sha256":"8868cad13928bcc223a1bdda89d55e237ff0a3285281b2741f836ec05bbfbfbd","source":{"kind":"arxiv","id":"2508.10975","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10975","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10975v2","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10975","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"RBUMVUJZFC6M","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"RBUMVUJZFC6MEI5B","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"RBUMVUJZ","created_at":"2026-07-05T11:56:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RBUMVUJZFC6MEI5BXXNITVK6EN","target":"record","payload":{"canonical_record":{"source":{"id":"2508.10975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:55:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f74c929428c052a999fed20deabcfc2400a5b6f41f2848c23d670395516d80d","abstract_canon_sha256":"fb1e6b8a3b1acd3b91ded9cc1f6d638d51a9086203d0f06882e09b9672ac32d1"},"schema_version":"1.0"},"canonical_sha256":"8868cad13928bcc223a1bdda89d55e237ff0a3285281b2741f836ec05bbfbfbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:22.779469Z","signature_b64":"3NF4J6mbmJw7lgdNR88cl6aqff/ZtO9ncEJSVzftFqpULXGMIa9VDRyJCsUJE7iyNJ9eHohdQIDQbHNt6aUYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8868cad13928bcc223a1bdda89d55e237ff0a3285281b2741f836ec05bbfbfbd","last_reissued_at":"2026-07-05T11:56:22.778990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:22.778990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.10975","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":"2026-07-05T11:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFt9xrz91/hyTUtfShRT0D4IzG/IZvnxPbI/V/8Lqo01yajfI9wGhOdvkYVVZjci84B7ySAYoaJZUN/d2ad0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:24:44.642306Z"},"content_sha256":"3a7e2f6bb95ada315be2bccb5ecfc1455bc1e4a7ec7d0c52a350947b6042f5b7","schema_version":"1.0","event_id":"sha256:3a7e2f6bb95ada315be2bccb5ecfc1455bc1e4a7ec7d0c52a350947b6042f5b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RBUMVUJZFC6MEI5BXXNITVK6EN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aldo Carranza, Alex Fang, Alvin Deng, Amro Abbas, Ari Morcos, Bogdan Gaza, Brett Larsen, Charvi Bannur, Christina Baek, Cody Blakeney, Darren Teh, DatologyAI: Pratyush Maini, David Schwab, Fan Pan, Haakon Mongstad, Haoli Yin, Jack Urbanek, Josh Wills, Kaleigh Mentzer, Luke Merrick, Matthew Leavitt, Parth Doshi, Paul Burstein, Ricardo Monti, Rishabh Adiga, Siddharth Joshi, Spandan Das, Vineeth Dorna, Zhengping Wang","submitted_at":"2025-08-14T17:55:47Z","abstract_excerpt":"Recent advances in large language model (LLM) pretraining have shown that simply scaling data quantity eventually leads to diminishing returns, hitting a data wall. In response, the use of synthetic data for pretraining has emerged as a promising paradigm for pushing the frontier of performance. Despite this, the factors affecting synthetic data quality remain poorly understood. In this work, we introduce BeyondWeb, a synthetic data generation framework that produces high-quality synthetic data for pretraining. BeyondWeb significantly extends the capabilities of traditional web-scale datasets,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10975","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/2508.10975/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":"2026-07-05T11:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eo5MpdvpsOH2KWTpsoEqx3DZ4jX2U7J5pbhrBvqlPdM7dKN/SOCWjLVPXa+P03HU2uMdq9WRldBG0nId/MY+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:24:44.643336Z"},"content_sha256":"276d512de5df6a3f9a36c8d85edc1cacf8a9e72d8afb6b2cd46fa37e3a895120","schema_version":"1.0","event_id":"sha256:276d512de5df6a3f9a36c8d85edc1cacf8a9e72d8afb6b2cd46fa37e3a895120"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/bundle.json","state_url":"https://pith.science/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/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":"2026-08-10T18:24:44Z","links":{"resolver":"https://pith.science/pith/RBUMVUJZFC6MEI5BXXNITVK6EN","bundle":"https://pith.science/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/bundle.json","state":"https://pith.science/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBUMVUJZFC6MEI5BXXNITVK6EN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RBUMVUJZFC6MEI5BXXNITVK6EN","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":"fb1e6b8a3b1acd3b91ded9cc1f6d638d51a9086203d0f06882e09b9672ac32d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:55:47Z","title_canon_sha256":"7f74c929428c052a999fed20deabcfc2400a5b6f41f2848c23d670395516d80d"},"schema_version":"1.0","source":{"id":"2508.10975","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10975","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10975v2","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10975","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"RBUMVUJZFC6M","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"RBUMVUJZFC6MEI5B","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"RBUMVUJZ","created_at":"2026-07-05T11:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:276d512de5df6a3f9a36c8d85edc1cacf8a9e72d8afb6b2cd46fa37e3a895120","target":"graph","created_at":"2026-07-05T11:56:22Z","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/2508.10975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language model (LLM) pretraining have shown that simply scaling data quantity eventually leads to diminishing returns, hitting a data wall. In response, the use of synthetic data for pretraining has emerged as a promising paradigm for pushing the frontier of performance. Despite this, the factors affecting synthetic data quality remain poorly understood. In this work, we introduce BeyondWeb, a synthetic data generation framework that produces high-quality synthetic data for pretraining. BeyondWeb significantly extends the capabilities of traditional web-scale datasets,","authors_text":"Aldo Carranza, Alex Fang, Alvin Deng, Amro Abbas, Ari Morcos, Bogdan Gaza, Brett Larsen, Charvi Bannur, Christina Baek, Cody Blakeney, Darren Teh, DatologyAI: Pratyush Maini, David Schwab, Fan Pan, Haakon Mongstad, Haoli Yin, Jack Urbanek, Josh Wills, Kaleigh Mentzer, Luke Merrick, Matthew Leavitt, Parth Doshi, Paul Burstein, Ricardo Monti, Rishabh Adiga, Siddharth Joshi, Spandan Das, Vineeth Dorna, Zhengping Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:55:47Z","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10975","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":"sha256:3a7e2f6bb95ada315be2bccb5ecfc1455bc1e4a7ec7d0c52a350947b6042f5b7","target":"record","created_at":"2026-07-05T11:56:22Z","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":"fb1e6b8a3b1acd3b91ded9cc1f6d638d51a9086203d0f06882e09b9672ac32d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:55:47Z","title_canon_sha256":"7f74c929428c052a999fed20deabcfc2400a5b6f41f2848c23d670395516d80d"},"schema_version":"1.0","source":{"id":"2508.10975","kind":"arxiv","version":2}},"canonical_sha256":"8868cad13928bcc223a1bdda89d55e237ff0a3285281b2741f836ec05bbfbfbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8868cad13928bcc223a1bdda89d55e237ff0a3285281b2741f836ec05bbfbfbd","first_computed_at":"2026-07-05T11:56:22.778990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:22.778990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3NF4J6mbmJw7lgdNR88cl6aqff/ZtO9ncEJSVzftFqpULXGMIa9VDRyJCsUJE7iyNJ9eHohdQIDQbHNt6aUYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:22.779469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10975","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a7e2f6bb95ada315be2bccb5ecfc1455bc1e4a7ec7d0c52a350947b6042f5b7","sha256:276d512de5df6a3f9a36c8d85edc1cacf8a9e72d8afb6b2cd46fa37e3a895120"],"state_sha256":"6a771294d8bedb9b12636bbbbb9d4505a4be75026ef0c6d1d8736397bf18a0fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qm4y9mWvGLEy3jWyw+weekkDCe+8HZpV/pUm8pD6L3SL9QT0td5AIvSr7Unb5cy4hc3WZrrh2C/r6SvV0JUoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:24:44.649504Z","bundle_sha256":"cfb3bc8154543e1c8803c3c5744a0dd7e3e2918329baa811cf7c5d3537859137"}}