{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YEM6NZCP54YQZU4LQRGVX4JVHA","short_pith_number":"pith:YEM6NZCP","canonical_record":{"source":{"id":"2506.10972","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe1cab30521e7350998cd66760423e2c04bff6399e1544726f24cb46a7111872","abstract_canon_sha256":"b7b16602b5c0a017972db8d9c129b912bad5a6f2322f0e0921855dfa4275285d"},"schema_version":"1.0"},"canonical_sha256":"c119e6e44fef310cd38b844d5bf135382d0906d42163226ee5e33b26289f7cc8","source":{"kind":"arxiv","id":"2506.10972","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10972","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10972v3","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10972","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"YEM6NZCP54YQ","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"YEM6NZCP54YQZU4L","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"YEM6NZCP","created_at":"2026-07-05T11:38:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YEM6NZCP54YQZU4LQRGVX4JVHA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.10972","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe1cab30521e7350998cd66760423e2c04bff6399e1544726f24cb46a7111872","abstract_canon_sha256":"b7b16602b5c0a017972db8d9c129b912bad5a6f2322f0e0921855dfa4275285d"},"schema_version":"1.0"},"canonical_sha256":"c119e6e44fef310cd38b844d5bf135382d0906d42163226ee5e33b26289f7cc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:07.643489Z","signature_b64":"TWlh9+7NoeV4S5NSdtgxyXo/9qH3b9EW6zcDStY2EMJIRvxvd0ptnhJW6yBO01H1+UkqJHK4274fnO76kgY7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c119e6e44fef310cd38b844d5bf135382d0906d42163226ee5e33b26289f7cc8","last_reissued_at":"2026-07-05T11:38:07.642824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:07.642824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.10972","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":"2026-07-05T11:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zMlcpKvb/Zjivq1rpcZXQ9h21Ak4kE+f0Q3eJrCD6e3YqDqzYMrxwIRZZvgG012K2e88hBDzyAPL11DdmWNbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:31:58.820612Z"},"content_sha256":"ee5f44a0003894c11941fe02893fd7e5b5181943df303ac406552f03bf9c9e1a","schema_version":"1.0","event_id":"sha256:ee5f44a0003894c11941fe02893fd7e5b5181943df303ac406552f03bf9c9e1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YEM6NZCP54YQZU4LQRGVX4JVHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daxin Jiang, Haoying Wang, Houyi Li, Ning Ding, Qiufeng Wang, Shijie Xuyang, Shuigeng Zhou, Wenzhen Zheng, Xiangyu Zhang, Zhenyu Ding, Zili Wang","submitted_at":"2025-06-12T17:59:23Z","abstract_excerpt":"Training Large Language Models (LLMs) is prohibitively expensive, creating a critical scaling gap where insights from small-scale experiments often fail to transfer to resource-intensive production systems, thereby hindering efficient innovation. To bridge this, we introduce Farseer, a novel and refined scaling law offering enhanced predictive accuracy across scales. By systematically constructing a model loss surface $L(N,D)$, Farseer achieves a significantly better fit to empirical data than prior laws (e.g., Chinchilla's law). Our methodology yields accurate, robust, and highly generalizabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10972","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/2506.10972/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":"2026-07-05T11:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCK4xt9+2dKOsSkrhafjb/y7qPR+nWIoDia1F2F7OgePA/hAhcV/fn3NXeubSM2MCbTeSlZ8w9t3eA28+R0xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:31:58.821361Z"},"content_sha256":"423dde58bd5d595ca86c347c94ef73ef2ac6032c525a0794929dfad1a9ebfe48","schema_version":"1.0","event_id":"sha256:423dde58bd5d595ca86c347c94ef73ef2ac6032c525a0794929dfad1a9ebfe48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/bundle.json","state_url":"https://pith.science/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/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":"2026-08-12T13:31:58Z","links":{"resolver":"https://pith.science/pith/YEM6NZCP54YQZU4LQRGVX4JVHA","bundle":"https://pith.science/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/bundle.json","state":"https://pith.science/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEM6NZCP54YQZU4LQRGVX4JVHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YEM6NZCP54YQZU4LQRGVX4JVHA","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":"b7b16602b5c0a017972db8d9c129b912bad5a6f2322f0e0921855dfa4275285d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:23Z","title_canon_sha256":"fe1cab30521e7350998cd66760423e2c04bff6399e1544726f24cb46a7111872"},"schema_version":"1.0","source":{"id":"2506.10972","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10972","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10972v3","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10972","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"YEM6NZCP54YQ","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"YEM6NZCP54YQZU4L","created_at":"2026-07-05T11:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"YEM6NZCP","created_at":"2026-07-05T11:38:07Z"}],"graph_snapshots":[{"event_id":"sha256:423dde58bd5d595ca86c347c94ef73ef2ac6032c525a0794929dfad1a9ebfe48","target":"graph","created_at":"2026-07-05T11:38:07Z","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/2506.10972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training Large Language Models (LLMs) is prohibitively expensive, creating a critical scaling gap where insights from small-scale experiments often fail to transfer to resource-intensive production systems, thereby hindering efficient innovation. To bridge this, we introduce Farseer, a novel and refined scaling law offering enhanced predictive accuracy across scales. By systematically constructing a model loss surface $L(N,D)$, Farseer achieves a significantly better fit to empirical data than prior laws (e.g., Chinchilla's law). Our methodology yields accurate, robust, and highly generalizabl","authors_text":"Daxin Jiang, Haoying Wang, Houyi Li, Ning Ding, Qiufeng Wang, Shijie Xuyang, Shuigeng Zhou, Wenzhen Zheng, Xiangyu Zhang, Zhenyu Ding, Zili Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:23Z","title":"Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10972","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:ee5f44a0003894c11941fe02893fd7e5b5181943df303ac406552f03bf9c9e1a","target":"record","created_at":"2026-07-05T11:38:07Z","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":"b7b16602b5c0a017972db8d9c129b912bad5a6f2322f0e0921855dfa4275285d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:23Z","title_canon_sha256":"fe1cab30521e7350998cd66760423e2c04bff6399e1544726f24cb46a7111872"},"schema_version":"1.0","source":{"id":"2506.10972","kind":"arxiv","version":3}},"canonical_sha256":"c119e6e44fef310cd38b844d5bf135382d0906d42163226ee5e33b26289f7cc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c119e6e44fef310cd38b844d5bf135382d0906d42163226ee5e33b26289f7cc8","first_computed_at":"2026-07-05T11:38:07.642824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:07.642824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TWlh9+7NoeV4S5NSdtgxyXo/9qH3b9EW6zcDStY2EMJIRvxvd0ptnhJW6yBO01H1+UkqJHK4274fnO76kgY7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:07.643489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10972","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee5f44a0003894c11941fe02893fd7e5b5181943df303ac406552f03bf9c9e1a","sha256:423dde58bd5d595ca86c347c94ef73ef2ac6032c525a0794929dfad1a9ebfe48"],"state_sha256":"2f590d8bfb65fc2589f1940f8006ada514198b7747efbbab765c7198992e3d4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pMEAHBL1rBxop4PQJnlXyre0FvpW3rGfDGv4lt+hBz/EFLdhcnzuUF92dCGcQYoKH1kGPzFmJXsM8wu7oxa7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:31:58.831236Z","bundle_sha256":"1ee72edcae451770b48c9d6d8995aeb3b15e8718a4edcb3fba2b2de6caf205cd"}}