{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NQ6X7PIEZ2T6SSTKVUVS77SHK4","short_pith_number":"pith:NQ6X7PIE","canonical_record":{"source":{"id":"2507.12466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:59:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a30ae9d2484791870edf6919e9067e26f20540ff5a60bb87e62d061e4b64a090","abstract_canon_sha256":"46a41873332a410815cad7cdb197a01be9ae6212a9409137adc78db5f0bf0eb8"},"schema_version":"1.0"},"canonical_sha256":"6c3d7fbd04cea7e94a6aad2b2ffe47570d0a120fa2b126a767aa06108d925c20","source":{"kind":"arxiv","id":"2507.12466","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12466","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12466v1","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12466","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"NQ6X7PIEZ2T6","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"NQ6X7PIEZ2T6SSTK","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"NQ6X7PIE","created_at":"2026-07-05T11:38:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NQ6X7PIEZ2T6SSTKVUVS77SHK4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:59:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a30ae9d2484791870edf6919e9067e26f20540ff5a60bb87e62d061e4b64a090","abstract_canon_sha256":"46a41873332a410815cad7cdb197a01be9ae6212a9409137adc78db5f0bf0eb8"},"schema_version":"1.0"},"canonical_sha256":"6c3d7fbd04cea7e94a6aad2b2ffe47570d0a120fa2b126a767aa06108d925c20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:20.807576Z","signature_b64":"tTH7ahoodjsOuEU5k24DiLOGA+AC/47SbDp6ScunTXbztI20x2r3AY9ubPu6H3EtyKf7FVUXej5nUiW8lyXXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3d7fbd04cea7e94a6aad2b2ffe47570d0a120fa2b126a767aa06108d925c20","last_reissued_at":"2026-07-05T11:38:20.807023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:20.807023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12466","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":"2026-07-05T11:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYlayYoZ4fFG24eTlMPlindiVCPgpTCUhTW2Pv9FuPB8nqmVXN66L3X3ks0cn2DR3pE5FcyV9vSn9VhilrI5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:19:08.388625Z"},"content_sha256":"0fdfe004ef6bd5c1b45ca873b84d1e183c07e3cc2b3a068171791807e4be44d8","schema_version":"1.0","event_id":"sha256:0fdfe004ef6bd5c1b45ca873b84d1e183c07e3cc2b3a068171791807e4be44d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NQ6X7PIEZ2T6SSTKVUVS77SHK4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models Improve When Pretraining Data Matches Target Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Afshin Dehghan, Alex Fang, Anders Boesen Lindbo Larsen, David Mizrahi, Jeffrey Li, Jesse Allardice, Josh Gardner, Suzie Petryk, Tom Gunter, Yuri Gorokhov","submitted_at":"2025-07-16T17:59:45Z","abstract_excerpt":"Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine accordingly. This raises a natural question: what happens when we make this optimization explicit? To explore this, we propose benchmark-targeted ranking (BETR), a simple method that selects pretraining documents based on similarity to benchmark training examples. BETR embeds benchmark examples and a sample of pretraining documents in a shared space, scores t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12466","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/2507.12466/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":"2026-07-05T11:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1m9P12RssM9WkxGy4ptH6KuCiAa4jPXay5qlB6d66CFZXPqJP/d4ywiqjwZEDY+aMB+Mi2ptN6iRnLN/lSGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:19:08.389010Z"},"content_sha256":"65bc0fca9ae5337ba3e00e2251d2d6972433315102a6badd44451a02b1413d9c","schema_version":"1.0","event_id":"sha256:65bc0fca9ae5337ba3e00e2251d2d6972433315102a6badd44451a02b1413d9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/bundle.json","state_url":"https://pith.science/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/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":"2026-07-07T11:19:08Z","links":{"resolver":"https://pith.science/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4","bundle":"https://pith.science/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/bundle.json","state":"https://pith.science/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQ6X7PIEZ2T6SSTKVUVS77SHK4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NQ6X7PIEZ2T6SSTKVUVS77SHK4","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":"46a41873332a410815cad7cdb197a01be9ae6212a9409137adc78db5f0bf0eb8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:59:45Z","title_canon_sha256":"a30ae9d2484791870edf6919e9067e26f20540ff5a60bb87e62d061e4b64a090"},"schema_version":"1.0","source":{"id":"2507.12466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12466","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12466v1","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12466","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"NQ6X7PIEZ2T6","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"NQ6X7PIEZ2T6SSTK","created_at":"2026-07-05T11:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"NQ6X7PIE","created_at":"2026-07-05T11:38:20Z"}],"graph_snapshots":[{"event_id":"sha256:65bc0fca9ae5337ba3e00e2251d2d6972433315102a6badd44451a02b1413d9c","target":"graph","created_at":"2026-07-05T11:38:20Z","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/2507.12466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine accordingly. This raises a natural question: what happens when we make this optimization explicit? To explore this, we propose benchmark-targeted ranking (BETR), a simple method that selects pretraining documents based on similarity to benchmark training examples. BETR embeds benchmark examples and a sample of pretraining documents in a shared space, scores t","authors_text":"Afshin Dehghan, Alex Fang, Anders Boesen Lindbo Larsen, David Mizrahi, Jeffrey Li, Jesse Allardice, Josh Gardner, Suzie Petryk, Tom Gunter, Yuri Gorokhov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:59:45Z","title":"Language Models Improve When Pretraining Data Matches Target Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12466","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":"sha256:0fdfe004ef6bd5c1b45ca873b84d1e183c07e3cc2b3a068171791807e4be44d8","target":"record","created_at":"2026-07-05T11:38:20Z","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":"46a41873332a410815cad7cdb197a01be9ae6212a9409137adc78db5f0bf0eb8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:59:45Z","title_canon_sha256":"a30ae9d2484791870edf6919e9067e26f20540ff5a60bb87e62d061e4b64a090"},"schema_version":"1.0","source":{"id":"2507.12466","kind":"arxiv","version":1}},"canonical_sha256":"6c3d7fbd04cea7e94a6aad2b2ffe47570d0a120fa2b126a767aa06108d925c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c3d7fbd04cea7e94a6aad2b2ffe47570d0a120fa2b126a767aa06108d925c20","first_computed_at":"2026-07-05T11:38:20.807023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:20.807023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTH7ahoodjsOuEU5k24DiLOGA+AC/47SbDp6ScunTXbztI20x2r3AY9ubPu6H3EtyKf7FVUXej5nUiW8lyXXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:20.807576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fdfe004ef6bd5c1b45ca873b84d1e183c07e3cc2b3a068171791807e4be44d8","sha256:65bc0fca9ae5337ba3e00e2251d2d6972433315102a6badd44451a02b1413d9c"],"state_sha256":"c9abb969b689d378b5d05faffac9b865169eb15b3ffb66adee29b440edc2d045"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9zhjRqKmBD9qSFr6Bh1BVBHrJDQGOwk1wqW+QNv6v2I6cfyt//FpAW2lwbdgb2FyVUMnvMFP++8mDuBM400AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:19:08.391075Z","bundle_sha256":"9b2360df4bba2dd21c8d298e10bcae354f7ef3074352152c3072b40a67cde855"}}