{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FSBVO47YPF2NT3N5E4UNCMX2HD","short_pith_number":"pith:FSBVO47Y","canonical_record":{"source":{"id":"2502.12120","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:45:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cc4618a395ac64e37ac649fa3515b9697d3aebedf057c2f666392e8ec6f108e8","abstract_canon_sha256":"0d10e906da89724f7de4cf358c471a9eb074ae8adb67ebe3820934bbcb338e12"},"schema_version":"1.0"},"canonical_sha256":"2c835773f87974d9edbd2728d132fa38db327fab110c3dcf17b961126d487390","source":{"kind":"arxiv","id":"2502.12120","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12120","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12120v3","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12120","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"FSBVO47YPF2N","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"FSBVO47YPF2NT3N5","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"FSBVO47Y","created_at":"2026-05-21T01:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FSBVO47YPF2NT3N5E4UNCMX2HD","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12120","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:45:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cc4618a395ac64e37ac649fa3515b9697d3aebedf057c2f666392e8ec6f108e8","abstract_canon_sha256":"0d10e906da89724f7de4cf358c471a9eb074ae8adb67ebe3820934bbcb338e12"},"schema_version":"1.0"},"canonical_sha256":"2c835773f87974d9edbd2728d132fa38db327fab110c3dcf17b961126d487390","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:04.409365Z","signature_b64":"0Vs+Z1wQamSxQXiPKdSU1FZRUQmeNd56cBnSHBLsCpTijXeuAsTv6/e/wj7sNVhh5seYrzOuayEL5UY+eRLhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c835773f87974d9edbd2728d132fa38db327fab110c3dcf17b961126d487390","last_reissued_at":"2026-05-21T01:05:04.408522Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:04.408522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12120","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts5DtfOW//e3L2HM1B3Dmut/m7U2RbTLDuCvaq57jf8NO2iYM2zqXVEbeMk2kPYpqu2yRx0g9MA+YF7mcU9JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:36:13.039174Z"},"content_sha256":"cd300d236a3ae3c6289c5e7a1aaad9e6c4e9b20f451896db60eddc6cf0ad6b21","schema_version":"1.0","event_id":"sha256:cd300d236a3ae3c6289c5e7a1aaad9e6c4e9b20f451896db60eddc6cf0ad6b21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FSBVO47YPF2NT3N5E4UNCMX2HD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Matthias Bethge, Prasanna Mayilvahanan, Sayak Mallick, Thadd\\\"aus Wiedemer, Wieland Brendel","submitted_at":"2025-02-17T18:45:25Z","abstract_excerpt":"Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss scaling laws that relate losses across pretraining datasets and downstream tasks have emerged as a powerful tool for understanding and improving LLM performance and generalization. In this work, we investigate which factors most strongly influence loss-to-loss scaling. Our experiments reveal that the pretraining data determines the scaling trend. In contrast, model size, optimization hyperparameters, tokenizer and even "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12120","kind":"arxiv","version":3},"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/2502.12120/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":"2026-05-21T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUAX0udPBgZgga+PNRu0wuHytMrWIpSAdaook3e6WLF2SLALmajR3itFHvICMCSCcs7pu2lDC7O+BM9A30BECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:36:13.039721Z"},"content_sha256":"e689b5f942107227fe837811b455f40888517ba0b1a732cdfbdcca12ce024ee1","schema_version":"1.0","event_id":"sha256:e689b5f942107227fe837811b455f40888517ba0b1a732cdfbdcca12ce024ee1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/bundle.json","state_url":"https://pith.science/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/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":"2026-05-25T00:36:13Z","links":{"resolver":"https://pith.science/pith/FSBVO47YPF2NT3N5E4UNCMX2HD","bundle":"https://pith.science/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/bundle.json","state":"https://pith.science/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSBVO47YPF2NT3N5E4UNCMX2HD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FSBVO47YPF2NT3N5E4UNCMX2HD","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":"0d10e906da89724f7de4cf358c471a9eb074ae8adb67ebe3820934bbcb338e12","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:45:25Z","title_canon_sha256":"cc4618a395ac64e37ac649fa3515b9697d3aebedf057c2f666392e8ec6f108e8"},"schema_version":"1.0","source":{"id":"2502.12120","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12120","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12120v3","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12120","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"FSBVO47YPF2N","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"FSBVO47YPF2NT3N5","created_at":"2026-05-21T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"FSBVO47Y","created_at":"2026-05-21T01:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:e689b5f942107227fe837811b455f40888517ba0b1a732cdfbdcca12ce024ee1","target":"graph","created_at":"2026-05-21T01:05:04Z","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/2502.12120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss scaling laws that relate losses across pretraining datasets and downstream tasks have emerged as a powerful tool for understanding and improving LLM performance and generalization. In this work, we investigate which factors most strongly influence loss-to-loss scaling. Our experiments reveal that the pretraining data determines the scaling trend. In contrast, model size, optimization hyperparameters, tokenizer and even ","authors_text":"Matthias Bethge, Prasanna Mayilvahanan, Sayak Mallick, Thadd\\\"aus Wiedemer, Wieland Brendel","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:45:25Z","title":"LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12120","kind":"arxiv","version":3},"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:cd300d236a3ae3c6289c5e7a1aaad9e6c4e9b20f451896db60eddc6cf0ad6b21","target":"record","created_at":"2026-05-21T01:05:04Z","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":"0d10e906da89724f7de4cf358c471a9eb074ae8adb67ebe3820934bbcb338e12","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:45:25Z","title_canon_sha256":"cc4618a395ac64e37ac649fa3515b9697d3aebedf057c2f666392e8ec6f108e8"},"schema_version":"1.0","source":{"id":"2502.12120","kind":"arxiv","version":3}},"canonical_sha256":"2c835773f87974d9edbd2728d132fa38db327fab110c3dcf17b961126d487390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c835773f87974d9edbd2728d132fa38db327fab110c3dcf17b961126d487390","first_computed_at":"2026-05-21T01:05:04.408522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:04.408522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Vs+Z1wQamSxQXiPKdSU1FZRUQmeNd56cBnSHBLsCpTijXeuAsTv6/e/wj7sNVhh5seYrzOuayEL5UY+eRLhDA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:04.409365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12120","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd300d236a3ae3c6289c5e7a1aaad9e6c4e9b20f451896db60eddc6cf0ad6b21","sha256:e689b5f942107227fe837811b455f40888517ba0b1a732cdfbdcca12ce024ee1"],"state_sha256":"615f9dadaa089865c9baa45b41495f52a8f821f51f4c7011fe082749fcbe3917"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XeTyhqAWPyJbYavguoHZUXHUXBnpccP/VOQ6pCzOn+EdAWp4ddl1Q/5ewD3vLASwkVu1iC202MR4B68FpLXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T00:36:13.043478Z","bundle_sha256":"2f7a713985adaec1fa3742f01ac095699b3204a371045646b684978a140aa0d8"}}