{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5FSPIXSVWVVERZZPAUD7ZXM3PL","short_pith_number":"pith:5FSPIXSV","canonical_record":{"source":{"id":"2607.25271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T04:18:49Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"fd2844f629236671201631d59146dad15ec846746e89e8a43cb0bdc2280c3bd0","abstract_canon_sha256":"b2a8483ed21bdef84d90f80051161731d23840d175aa6c428c3f2e6376ced998"},"schema_version":"1.0"},"canonical_sha256":"e964f45e55b56a48e72f0507fcdd9b7ac8280c750fb5917d0010017b7da482be","source":{"kind":"arxiv","id":"2607.25271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25271","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25271v1","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25271","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"5FSPIXSVWVVE","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"5FSPIXSVWVVERZZP","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"5FSPIXSV","created_at":"2026-07-29T00:25:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5FSPIXSVWVVERZZPAUD7ZXM3PL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.25271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T04:18:49Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"fd2844f629236671201631d59146dad15ec846746e89e8a43cb0bdc2280c3bd0","abstract_canon_sha256":"b2a8483ed21bdef84d90f80051161731d23840d175aa6c428c3f2e6376ced998"},"schema_version":"1.0"},"canonical_sha256":"e964f45e55b56a48e72f0507fcdd9b7ac8280c750fb5917d0010017b7da482be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:12.060243Z","signature_b64":"+fuMtPKw/Vi16TV0BbaiegCZoBMbqG+Af3QGupds98C7F09ijGBba+Bv/SaQUyhsgpDzIbWcWeYE7Sgd4tCnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e964f45e55b56a48e72f0507fcdd9b7ac8280c750fb5917d0010017b7da482be","last_reissued_at":"2026-07-29T00:25:12.059377Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:12.059377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.25271","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":"2026-07-29T00:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKQsS2p4kqYNA5Wwzag0uxItuyIa8yDtSc+QTw21QdgkX/0r8LhdC2fQa0WcIJMe/LPHdtClYb7GU1XxbALGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:51:33.132673Z"},"content_sha256":"d4778692ce437b8e2f473275f7775d33dfedbc7b44e8e711eb9b39afce77df4f","schema_version":"1.0","event_id":"sha256:d4778692ce437b8e2f473275f7775d33dfedbc7b44e8e711eb9b39afce77df4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5FSPIXSVWVVERZZPAUD7ZXM3PL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Compute- and Data-Optimal Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Kimia Hamidieh, Tian Qin","submitted_at":"2026-07-28T04:18:49Z","abstract_excerpt":"Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data (CD) scaling laws, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound. CD scaling extends classical scaling laws by introducing a token-effectiveness function, $\\eta$, which quantifies the value of a derived token-produced, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25271","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/2607.25271/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":"2026-07-29T00:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuKlat2sor61aIoIsl7GQ8XNDet+rhNt08TDRSoHBDePFMux21MuCTsjOUaKiDgLcCsy599z8sFTNLcvmt5NAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:51:33.133595Z"},"content_sha256":"d0caf3dabcb99c7743118b463e46b73a0b654af39be42a153dc384bc2679ddc5","schema_version":"1.0","event_id":"sha256:d0caf3dabcb99c7743118b463e46b73a0b654af39be42a153dc384bc2679ddc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/bundle.json","state_url":"https://pith.science/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/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":"2026-08-01T20:51:33Z","links":{"resolver":"https://pith.science/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL","bundle":"https://pith.science/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/bundle.json","state":"https://pith.science/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FSPIXSVWVVERZZPAUD7ZXM3PL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5FSPIXSVWVVERZZPAUD7ZXM3PL","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":"b2a8483ed21bdef84d90f80051161731d23840d175aa6c428c3f2e6376ced998","cross_cats_sorted":["cs.AI","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T04:18:49Z","title_canon_sha256":"fd2844f629236671201631d59146dad15ec846746e89e8a43cb0bdc2280c3bd0"},"schema_version":"1.0","source":{"id":"2607.25271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25271","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25271v1","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25271","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"5FSPIXSVWVVE","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"5FSPIXSVWVVERZZP","created_at":"2026-07-29T00:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"5FSPIXSV","created_at":"2026-07-29T00:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:d0caf3dabcb99c7743118b463e46b73a0b654af39be42a153dc384bc2679ddc5","target":"graph","created_at":"2026-07-29T00:25:12Z","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/2607.25271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data (CD) scaling laws, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound. CD scaling extends classical scaling laws by introducing a token-effectiveness function, $\\eta$, which quantifies the value of a derived token-produced, ","authors_text":"David Alvarez-Melis, Kimia Hamidieh, Tian Qin","cross_cats":["cs.AI","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T04:18:49Z","title":"Bridging Compute- and Data-Optimal Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25271","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:d4778692ce437b8e2f473275f7775d33dfedbc7b44e8e711eb9b39afce77df4f","target":"record","created_at":"2026-07-29T00:25:12Z","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":"b2a8483ed21bdef84d90f80051161731d23840d175aa6c428c3f2e6376ced998","cross_cats_sorted":["cs.AI","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T04:18:49Z","title_canon_sha256":"fd2844f629236671201631d59146dad15ec846746e89e8a43cb0bdc2280c3bd0"},"schema_version":"1.0","source":{"id":"2607.25271","kind":"arxiv","version":1}},"canonical_sha256":"e964f45e55b56a48e72f0507fcdd9b7ac8280c750fb5917d0010017b7da482be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e964f45e55b56a48e72f0507fcdd9b7ac8280c750fb5917d0010017b7da482be","first_computed_at":"2026-07-29T00:25:12.059377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:12.059377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+fuMtPKw/Vi16TV0BbaiegCZoBMbqG+Af3QGupds98C7F09ijGBba+Bv/SaQUyhsgpDzIbWcWeYE7Sgd4tCnDg==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:12.060243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4778692ce437b8e2f473275f7775d33dfedbc7b44e8e711eb9b39afce77df4f","sha256:d0caf3dabcb99c7743118b463e46b73a0b654af39be42a153dc384bc2679ddc5"],"state_sha256":"f24abd2e95ff72b86f873008574f95d4bb0dbda1cf6ae393158e465711f4c0c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwicSJLlVZPgkpuITropIHFsayVYAT+hP1BGO/5iaPidszC07szt0wsnD6dTivAuSEUiAYlRE0TU2L2hgNz2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T20:51:33.140018Z","bundle_sha256":"133b67f962188db29623f97e5efba4b79eeffdfe20807454698edb4633c8f47d"}}