{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P7VB6OOVA4MI4IC4EXDKNMOVJK","short_pith_number":"pith:P7VB6OOV","canonical_record":{"source":{"id":"2607.04969","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:57:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9b3009f8b02edea43e8b3147568f08fdaae4aaeab83465814707767f80ba699f","abstract_canon_sha256":"da35bea28bcdb6b1fedb1997aecc944f6c8af22960ceb19fcb07fd6cb273df62"},"schema_version":"1.0"},"canonical_sha256":"7fea1f39d507188e205c25c6a6b1d54aa8b52fa258e91fa67bb683c98bfa6070","source":{"kind":"arxiv","id":"2607.04969","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04969","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04969v1","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04969","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"P7VB6OOVA4MI","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"P7VB6OOVA4MI4IC4","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"P7VB6OOV","created_at":"2026-07-07T02:20:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P7VB6OOVA4MI4IC4EXDKNMOVJK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04969","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:57:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9b3009f8b02edea43e8b3147568f08fdaae4aaeab83465814707767f80ba699f","abstract_canon_sha256":"da35bea28bcdb6b1fedb1997aecc944f6c8af22960ceb19fcb07fd6cb273df62"},"schema_version":"1.0"},"canonical_sha256":"7fea1f39d507188e205c25c6a6b1d54aa8b52fa258e91fa67bb683c98bfa6070","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:16.054475Z","signature_b64":"7x6Hc4VUd35P5+BgGEuOjJZOR16ehOuOriDlyc1hTQLM7fgqNB/0raoHUwLWf3qgQIulaWhveMjku8AoQKauAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fea1f39d507188e205c25c6a6b1d54aa8b52fa258e91fa67bb683c98bfa6070","last_reissued_at":"2026-07-07T02:20:16.053715Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:16.053715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04969","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RcM8H2YNUogCoglclNK6ATDlwAJMMsfPAuEepo3ewqD5jM2O8bYrbBrFgXjTMDf0+KeB+XtVD3STpl6Od7fYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:23:21.121836Z"},"content_sha256":"2724e198218978399e781cd6b8ca5b967683fbb811fb9ba730372b1d5b910213","schema_version":"1.0","event_id":"sha256:2724e198218978399e781cd6b8ca5b967683fbb811fb9ba730372b1d5b910213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P7VB6OOVA4MI4IC4EXDKNMOVJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Abhay Kumar, Cong Zeng, Dhia Eddine Rhaiem, Hakim Hacid, Ilyas Chahed, Jingwei Zuo, Maksim Velikanov, Pasquale Balsebre, Younes Belkada","submitted_at":"2026-07-06T11:57:32Z","abstract_excerpt":"The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited high-quality data can improve both model performance and sample efficiency. Meanwhile, excessive repetition introduces the risk of overfitting and diminishing returns. Determining when and how to reuse data effectively thus emerges as a natural but under-explored question. Through a novel observation of model's \"Memorization Window\" signals derived from loss retention dynamics and downstream evaluation scores, we propose \"Memorization-guided Data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04969","kind":"arxiv","version":1},"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/2607.04969/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":"2026-07-07T02:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRcbTmkQtFhJ5RfByIzFJXfcmN92LacS1heRlme8IS90HC/80wRND6TaRw8IkHo42lKk3CCsWe9jCEetqQe4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:23:21.122213Z"},"content_sha256":"3483071f5a36f9f3a630c52f5fc5d8392cdb1beebc53540bf8c240cf48f2a6ad","schema_version":"1.0","event_id":"sha256:3483071f5a36f9f3a630c52f5fc5d8392cdb1beebc53540bf8c240cf48f2a6ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/bundle.json","state_url":"https://pith.science/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/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":"2026-07-09T04:23:21Z","links":{"resolver":"https://pith.science/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK","bundle":"https://pith.science/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/bundle.json","state":"https://pith.science/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7VB6OOVA4MI4IC4EXDKNMOVJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P7VB6OOVA4MI4IC4EXDKNMOVJK","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":"da35bea28bcdb6b1fedb1997aecc944f6c8af22960ceb19fcb07fd6cb273df62","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:57:32Z","title_canon_sha256":"9b3009f8b02edea43e8b3147568f08fdaae4aaeab83465814707767f80ba699f"},"schema_version":"1.0","source":{"id":"2607.04969","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04969","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04969v1","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04969","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"P7VB6OOVA4MI","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"P7VB6OOVA4MI4IC4","created_at":"2026-07-07T02:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"P7VB6OOV","created_at":"2026-07-07T02:20:16Z"}],"graph_snapshots":[{"event_id":"sha256:3483071f5a36f9f3a630c52f5fc5d8392cdb1beebc53540bf8c240cf48f2a6ad","target":"graph","created_at":"2026-07-07T02:20:16Z","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/2607.04969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited high-quality data can improve both model performance and sample efficiency. Meanwhile, excessive repetition introduces the risk of overfitting and diminishing returns. Determining when and how to reuse data effectively thus emerges as a natural but under-explored question. Through a novel observation of model's \"Memorization Window\" signals derived from loss retention dynamics and downstream evaluation scores, we propose \"Memorization-guided Data","authors_text":"Abhay Kumar, Cong Zeng, Dhia Eddine Rhaiem, Hakim Hacid, Ilyas Chahed, Jingwei Zuo, Maksim Velikanov, Pasquale Balsebre, Younes Belkada","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:57:32Z","title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04969","kind":"arxiv","version":1},"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":"sha256:2724e198218978399e781cd6b8ca5b967683fbb811fb9ba730372b1d5b910213","target":"record","created_at":"2026-07-07T02:20:16Z","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":"da35bea28bcdb6b1fedb1997aecc944f6c8af22960ceb19fcb07fd6cb273df62","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:57:32Z","title_canon_sha256":"9b3009f8b02edea43e8b3147568f08fdaae4aaeab83465814707767f80ba699f"},"schema_version":"1.0","source":{"id":"2607.04969","kind":"arxiv","version":1}},"canonical_sha256":"7fea1f39d507188e205c25c6a6b1d54aa8b52fa258e91fa67bb683c98bfa6070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fea1f39d507188e205c25c6a6b1d54aa8b52fa258e91fa67bb683c98bfa6070","first_computed_at":"2026-07-07T02:20:16.053715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:20:16.053715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7x6Hc4VUd35P5+BgGEuOjJZOR16ehOuOriDlyc1hTQLM7fgqNB/0raoHUwLWf3qgQIulaWhveMjku8AoQKauAg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:20:16.054475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04969","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2724e198218978399e781cd6b8ca5b967683fbb811fb9ba730372b1d5b910213","sha256:3483071f5a36f9f3a630c52f5fc5d8392cdb1beebc53540bf8c240cf48f2a6ad"],"state_sha256":"74f0c22d7846bc394858abc25c97da615831807f7b7eb25b07af3672ac76e95f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSG4SyJqntEE/IsXR7rBxH2olQX1Voi1Qcxw1CcDwSeZZ5dIcs3D2JSVtukVwTEszTIKl2r0dwnPdn0MBP6PDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:23:21.124704Z","bundle_sha256":"689371b2fcde4aab7d353ac6195a87e1aa777847a7316804bb9d432717a58fa9"}}