Metraipolis › archive › dc_2bbcdb4991b9
Capability Emergence Can Be Forecast: Per-Seed, In Advance, With Calibrated Intervals, Certified False Alarms, and a Blind Pre-Registered Gate — arXiv:2609.19000
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19000
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:04:58.190Z
- SHA-256 of the archived text
a8684139293a75089b2dacab27427a72b8d929b30ff7071dcb1cc1e41acd0671- Stable URL of this page
https://metraipolis.com/documento/dc_2bbcdb4991b9
How to cite
Capability Emergence Can Be Forecast: Per-Seed, In Advance, With Calibrated Intervals, Certified False Alarms, and a Blind Pre-Registered Gate — arXiv:2609.19000 — arXiv (en), https://arxiv.org/abs/2609.19000 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bbcdb4991b9 (Metraipolis archive dc_2bbcdb4991b9, sha256 a8684139293a75089b2dacab27427a72b8d929b30ff7071dcb1cc1e41acd0671)
BibTeX
@misc{dc2bbcdb4991b9,
title = {Capability Emergence Can Be Forecast: Per-Seed, In Advance, With Calibrated Intervals, Certified False Alarms, and a Blind Pre-Registered Gate — arXiv:2609.19000},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19000},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bbcdb4991b9; sha256 a8684139293a75089b2dacab27427a72b8d929b30ff7071dcb1cc1e41acd0671},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19000. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Emergent capabilities are widely treated as unpredictable: loss improves smoothly while abilities appear abruptly. Prior work offers early-warning indicators but never scores them as forecasts: no lead time at controlled false-alarm rate, no calibration, no negatives, no blind tests. We supply that discipline and show that, in grokking model systems and small language models, emergence timing is forecastable per run, in advance, with calibrated uncertainty. Across 30 transformers at identical configuration, the formation time of the previous-token head forecasts each seed's induction-head emergence at Spearman rho=0.977 with median lead 975 steps (~15% of training); a best-case loss rule ties the ranking with 50-step lead (a nowcast). Conformal intervals covered 15/15 held-out seeds, and the frozen rule passed blind pre-registered gates on TWO never-seen configurations (10/10 and 9/10 coverage). A trap-language rung then attacked our own rule as pre-registered: where previous-token context pays for the task itself, the bare precursor false-alarms on 10/10 capability-blocked runs, while the mechanism-composed conjunction is certified in both language classes (0 false alarms) and times emergence at rho=1.000. Finally, a gap-origin study broke the fixed offset (both lr and batch move the gap ~2.3x; no external clock owns it) and revealed the law beneath: across 80 valid-anchor runs the anchor fires at 0.843 of time-to-emergence -- t_event ~= 1.19 x t_anchor -- and this multiplicative rule passed its own blind gate (5/5) at a third unseen configuration. False alarms are certified against 33 manufactured negatives. The precursor leads across 3 public model families (Pythia, OLMo, OLMo-2; 7 suites), with OLMo-2 at 1B tokens showing precursor formed, capability absent. Four pre-registered kill criteria fired and are reported. Every freeze precedes its data in a public commit chain. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.19000 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T14:08:19.165Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).