{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3DDC4ATHSX6PEVCYZYOJS6NP4D","short_pith_number":"pith:3DDC4ATH","canonical_record":{"source":{"id":"2502.04235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T17:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"7916f8e48d74a41f60e6f13d29d9d670be8ff0401aef736f949d46a62cc89227","abstract_canon_sha256":"73766639dac4e8f32daa8f6273f793eb9a38b7e68a285a4de3e9f9389429b9d3"},"schema_version":"1.0"},"canonical_sha256":"d8c62e026795fcf25458ce1c9979afe0ec804f1dca64ab626fbc1dcc48b585e9","source":{"kind":"arxiv","id":"2502.04235","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04235","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04235v2","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04235","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"3DDC4ATHSX6P","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"3DDC4ATHSX6PEVCY","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"3DDC4ATH","created_at":"2026-07-05T11:04:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3DDC4ATHSX6PEVCYZYOJS6NP4D","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T17:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"7916f8e48d74a41f60e6f13d29d9d670be8ff0401aef736f949d46a62cc89227","abstract_canon_sha256":"73766639dac4e8f32daa8f6273f793eb9a38b7e68a285a4de3e9f9389429b9d3"},"schema_version":"1.0"},"canonical_sha256":"d8c62e026795fcf25458ce1c9979afe0ec804f1dca64ab626fbc1dcc48b585e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:45.267256Z","signature_b64":"SBbu572pc2trPMYFRPMUiM3BSSATP6v+RgmkMyhE9Q2DTgs8837TZKhwFruIlQUfytBF93p/RaG7nHn2kQmTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c62e026795fcf25458ce1c9979afe0ec804f1dca64ab626fbc1dcc48b585e9","last_reissued_at":"2026-07-05T11:04:45.266730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:45.266730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04235","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":"2026-07-05T11:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Da3ctqTrQCOqg7RU8iq/BRXmz+cfvqMdfgmGBGw2xhnItmKKyONsSOuTe98UfALV0AanK1TlJdonAD+niQHJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T01:48:55.580727Z"},"content_sha256":"e5c743f219d1d65cdaf11eee605d8620de4842f176d04bc8c9147cfc95d26500","schema_version":"1.0","event_id":"sha256:e5c743f219d1d65cdaf11eee605d8620de4842f176d04bc8c9147cfc95d26500"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3DDC4ATHSX6PEVCYZYOJS6NP4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reformulation for Pretraining Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenggang Li, Ge Zhang, Ke Shen, Ruijie Zhu, Xintong Hao","submitted_at":"2025-02-06T17:19:55Z","abstract_excerpt":"Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive data repetition during training. To overcome this critical bottleneck, we propose the Massive Genre-Audience(MGA) reformulation method, a lightweight and scalable data augmentation technique inspired by synthetic data methodologies. MGA systematically reformulates existing corpora into diverse, contextually-rich variations to mitigate the negative effects of repetition, and we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04235","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/2502.04235/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":"2026-07-05T11:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gcLI4BuokprczkZb8ab20ozlM5ZJDlRCgm8GPHMUEdPPLDzmBeY7aj6mmfTAmsbow3IChz/Y6vJXKg1yydDbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T01:48:55.581099Z"},"content_sha256":"016cfb3b8bef3d1f6e6e888408d12e3866720fb84c9eb30d9a929eb9cd09a586","schema_version":"1.0","event_id":"sha256:016cfb3b8bef3d1f6e6e888408d12e3866720fb84c9eb30d9a929eb9cd09a586"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/bundle.json","state_url":"https://pith.science/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/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":"2026-07-25T01:48:55Z","links":{"resolver":"https://pith.science/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D","bundle":"https://pith.science/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/bundle.json","state":"https://pith.science/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DDC4ATHSX6PEVCYZYOJS6NP4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3DDC4ATHSX6PEVCYZYOJS6NP4D","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":"73766639dac4e8f32daa8f6273f793eb9a38b7e68a285a4de3e9f9389429b9d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T17:19:55Z","title_canon_sha256":"7916f8e48d74a41f60e6f13d29d9d670be8ff0401aef736f949d46a62cc89227"},"schema_version":"1.0","source":{"id":"2502.04235","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04235","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04235v2","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04235","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"3DDC4ATHSX6P","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"3DDC4ATHSX6PEVCY","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"3DDC4ATH","created_at":"2026-07-05T11:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:016cfb3b8bef3d1f6e6e888408d12e3866720fb84c9eb30d9a929eb9cd09a586","target":"graph","created_at":"2026-07-05T11:04:45Z","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/2502.04235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive data repetition during training. To overcome this critical bottleneck, we propose the Massive Genre-Audience(MGA) reformulation method, a lightweight and scalable data augmentation technique inspired by synthetic data methodologies. MGA systematically reformulates existing corpora into diverse, contextually-rich variations to mitigate the negative effects of repetition, and we ","authors_text":"Chenggang Li, Ge Zhang, Ke Shen, Ruijie Zhu, Xintong Hao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T17:19:55Z","title":"Reformulation for Pretraining Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04235","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:e5c743f219d1d65cdaf11eee605d8620de4842f176d04bc8c9147cfc95d26500","target":"record","created_at":"2026-07-05T11:04:45Z","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":"73766639dac4e8f32daa8f6273f793eb9a38b7e68a285a4de3e9f9389429b9d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T17:19:55Z","title_canon_sha256":"7916f8e48d74a41f60e6f13d29d9d670be8ff0401aef736f949d46a62cc89227"},"schema_version":"1.0","source":{"id":"2502.04235","kind":"arxiv","version":2}},"canonical_sha256":"d8c62e026795fcf25458ce1c9979afe0ec804f1dca64ab626fbc1dcc48b585e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8c62e026795fcf25458ce1c9979afe0ec804f1dca64ab626fbc1dcc48b585e9","first_computed_at":"2026-07-05T11:04:45.266730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:45.266730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SBbu572pc2trPMYFRPMUiM3BSSATP6v+RgmkMyhE9Q2DTgs8837TZKhwFruIlQUfytBF93p/RaG7nHn2kQmTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:45.267256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04235","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5c743f219d1d65cdaf11eee605d8620de4842f176d04bc8c9147cfc95d26500","sha256:016cfb3b8bef3d1f6e6e888408d12e3866720fb84c9eb30d9a929eb9cd09a586"],"state_sha256":"83fd2b732c1bc2a98d309458f68e7f9dc8757ea78b483e80763d4305f5c259c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3kBf/tDuHdYDAKBQ/yJzwMTA8ktuokOXOEgufD4HDMsvyHVhUWlH6Gfjm1m+fKVAoim2Or7bHKBTjAPf5JQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T01:48:55.583256Z","bundle_sha256":"6ba337d51a5772453d673130635a901e1ed834ce29b4411de1f3e0322519e4f2"}}