{"schema_version":"1.0.0","project":"Astra × Fable — an operator-run public forecasting experiment","generated_at":"2026-09-15T02:05:39.900Z","canonical_ledger":"https://github.com/yehorcallmedai-maker/yehor.ai/blob/main/content/forecasts/ledger.json","capabilities":{"read":true,"submissions":false,"live_feed":false,"automated_spending":false},"creation_routes":{"astra":"/forecast/observatory","fable":"/forecast/ledger","shared":"/forecast","research":"/forecast/lab"},"usage":{"status":"not_connected","actual_provider_cost":null,"available_funds":null},"seal_check":{"count":12,"checkedAt":"2026-09-15T02:05:39.900Z"},"scoring":{"rule":"brier","starting_credits":1000,"credit_formula":"delta = 100 × (1 − 4 × brier). A coin flip (p = 0.5) earns 0. p = 0.85 earns +91 when right and −189 when wrong.","void_policy":"A forecast is voided, not scored, when the forecaster could influence the outcome or the outcome cannot be established."},"interpretation":"Recorded ledger state, not independently verified settlement or a model ranking. Read the review annotations before scoring comparisons.","entries":[{"id":"F-001","forecaster":"astra","scale":"micro","horizon":"1 minute","question":"Yehor is still looking at or interacting with the same computer one minute after the forecast is issued.","probability":0.85,"locked_at":"2026-09-13T01:47:32Z","deadline":"2026-09-13T01:48:32Z","success_rule":"At the deadline Yehor is looking at or interacting with that computer. Being nearby is insufficient.","conflict_of_interest":false,"status":"resolved","outcome":"yes","resolved_at":"2026-09-13T01:55:00Z","evidence":"Self-report by Yehor in the Astra session at 03:55 Paris time. Not independently observed.","note":"Continuation forecast. The naïve baseline 'current activity continues' would also have succeeded, so this shows calibration, not edge.","seal":"c8ec30641f3abc82df988ff5ba4974801cd7cf70dc32f1b00f368174def90cce","round":"warm-up","title":"Still at the computer after one minute"},{"id":"F-002","forecaster":"fable","scale":"micro","horizon":"10 minutes","question":"Before the deadline Yehor switches focus to the other assistant window visible in his screenshot and sends at least one message there.","probability":0.7,"locked_at":"2026-09-13T02:34:42Z","deadline":"2026-09-13T02:44:42Z","success_rule":"Yes only if a message was sent in the other window before the deadline. Reading it does not count.","conflict_of_interest":false,"status":"resolved","outcome":"yes","resolved_at":"2026-09-13T03:20:22Z","evidence":"Self-report by Yehor in the Fable session, answered 'Yes' to the question of whether a message was sent in the other window between 02:34:42Z and 02:44:42Z. Reported after the deadline; not independently observed. The screenshot Yehor attached at 02:54Z shows a new message typed in that window, consistent with the report.","note":"First change forecast, chosen to beat the continuation baseline rather than repeat it.","seal":"07a66b62f624f83b6229857fbdf9a63f409629c5213d57fb98152545949bd764","round":"competition","independence":"blind","title":"A message in the other assistant window"},{"id":"F-003","forecaster":"fable","scale":"micro","horizon":"1 day","question":"At least one command or edit is run in the yehor.ai repository within 24 hours of the forecast.","probability":0.6,"locked_at":"2026-09-13T02:34:42Z","deadline":"2026-09-14T02:34:42Z","success_rule":"A commit or working-tree change in the yehor.ai repository between lock and deadline.","conflict_of_interest":false,"status":"void","outcome":null,"resolved_at":"2026-09-13T02:52:32Z","evidence":"Voided: 18 minutes after locking, Fable itself was asked to build this page in that repository. The forecaster could fulfil its own forecast.","note":"Kept in the ledger as the first recorded instance of the void policy.","seal":"fc38baeae4804ba2b77dc9353085fd621de5aedfb4ddd9fab83c00e4df12079c","title":"Activity in the repository within a day"},{"id":"F-004","forecaster":"fable","scale":"macro","horizon":"End of 2026","question":"Anthropic is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.6,"locked_at":"2026-09-13T02:52:32Z","deadline":"2026-12-31T23:59:59Z","success_rule":"Resolves as the cited market resolves. Market URL and resolution criteria to be recorded on this entry before scoring; until then the entry is open but unscoreable.","conflict_of_interest":true,"market":{"label":"Market price at lock","probability":0.67,"observed_at":"2026-09-13T02:30:00Z"},"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Fable shrank the market price toward uncertainty because of the 3.5-month horizon and its June 2026 knowledge cutoff. Conflict of interest: Fable is an Anthropic model. Verified by Fable on 2026-09-13 directly against Polymarket's API: event 'Which company has best AI model end of 2026?', https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Resolves on the LMArena text leaderboard as checked 2026-12-31 12:00 ET; ties broken by rank, then unrounded Arena score, then company name alphabetically. Astra's earlier report matched. Market price re-observed 2026-09-13T03:20:00Z: 0.695.","seal":"8bc04bdf3ef014383329c283963dd910a9f546ee593c52b8ffa7e88568504d3c","independence":"blind","title":"Anthropic leads AI at year-end"},{"id":"F-005","forecaster":"fable","scale":"macro","horizon":"End of 2026","question":"OpenAI is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.18,"locked_at":"2026-09-13T02:52:32Z","deadline":"2026-12-31T23:59:59Z","success_rule":"Resolves as the cited market resolves. Same open criteria as F-004.","conflict_of_interest":false,"market":{"label":"Market price at lock","probability":0.1,"observed_at":"2026-09-13T02:30:00Z"},"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Resolution rule as reported by Astra (unverified against the market page): the Arena text leaderboard at 12:00 Eastern on 31 December 2026, with tie-break rules. Market URL still to be recorded. Verified by Fable on 2026-09-13 directly against Polymarket's API: event 'Which company has best AI model end of 2026?', https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Resolves on the LMArena text leaderboard as checked 2026-12-31 12:00 ET; ties broken by rank, then unrounded Arena score, then company name alphabetically. Astra's earlier report matched. Market price re-observed 2026-09-13T03:20:00Z: 0.120.","seal":"2e6ecb241217a4512aa655214f930a097a99e85636e92f3ca7e2d51797b12296","independence":"blind","title":"OpenAI leads AI at year-end"},{"id":"F-006","forecaster":"fable","scale":"macro","horizon":"End of 2026","question":"Google is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.15,"locked_at":"2026-09-13T02:52:32Z","deadline":"2026-12-31T23:59:59Z","success_rule":"Resolves as the cited market resolves. Same open criteria as F-004.","conflict_of_interest":false,"market":{"label":"Market price at lock","probability":0.08,"observed_at":"2026-09-13T02:30:00Z"},"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Resolution rule as reported by Astra (unverified against the market page): the Arena text leaderboard at 12:00 Eastern on 31 December 2026, with tie-break rules. Market URL still to be recorded. Verified by Fable on 2026-09-13 directly against Polymarket's API: event 'Which company has best AI model end of 2026?', https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Resolves on the LMArena text leaderboard as checked 2026-12-31 12:00 ET; ties broken by rank, then unrounded Arena score, then company name alphabetically. Astra's earlier report matched. Market price re-observed 2026-09-13T03:20:00Z: 0.095.","seal":"f6a60edcee196c60ebf3eafabfc8bdd540c4efbf5ba018474fa2aaf7536f6ee1","independence":"blind","title":"Google leads AI at year-end"},{"id":"F-007","forecaster":"astra","scale":"macro","horizon":"End of 2026","question":"Anthropic is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.6,"locked_at":"2026-09-13T03:22:18Z","deadline":"2026-12-31T17:00:00Z","success_rule":"Yes iff Anthropic is the company selected by the cited market: https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Arena text leaderboard, style control off, checked 2026-12-31 12:00 America/New_York (17:00 UTC); lowest numeric rank, then highest unrounded Arena score, then company alphabetical order. If leaderboard unavailable, first available check afterward. If the source is permanently unavailable or disputed, await referee resolution; do not invent an outcome.","conflict_of_interest":false,"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Informed forecast: Astra read Fable F-004 to F-006 and market context before locking. Subjective distribution: Anthropic 60%, OpenAI 20%, Google 15%, all other companies combined 5%. Leading current market contender remains favored, with uncertainty about subsequent releases and leaderboard variation; no claimed predictive edge. All three are correlated outcomes of one event, not three independent trials. No trade or spending. Timestamp is the local UTC clock at file creation; commit time is the outer bound of the lock.","seal":"fd6df3464a083e830cda06f7eec78bd219f8ddaf3e17045b505c5a56c17f2e4f","round":"competition","independence":"informed","title":"Anthropic leads AI at year-end"},{"id":"F-008","forecaster":"astra","scale":"macro","horizon":"End of 2026","question":"OpenAI is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.2,"locked_at":"2026-09-13T03:22:18Z","deadline":"2026-12-31T17:00:00Z","success_rule":"Yes iff OpenAI is the company selected by the cited market: https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Arena text leaderboard, style control off, checked 2026-12-31 12:00 America/New_York (17:00 UTC); lowest numeric rank, then highest unrounded Arena score, then company alphabetical order. If leaderboard unavailable, first available check afterward. If the source is permanently unavailable or disputed, await referee resolution; do not invent an outcome.","conflict_of_interest":true,"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Informed forecast: Astra read Fable F-004 to F-006 and market context before locking. Subjective distribution: Anthropic 60%, OpenAI 20%, Google 15%, all other companies combined 5%. Leading current market contender remains favored, with uncertainty about subsequent releases and leaderboard variation; no claimed predictive edge. All three are correlated outcomes of one event, not three independent trials. No trade or spending. Timestamp is the local UTC clock at file creation; commit time is the outer bound of the lock.","seal":"fd3a663dd3ef0570140573c4b9385ecef9c121c060843fdcd5b46e7cf9f00933","round":"competition","independence":"informed","title":"OpenAI leads AI at year-end"},{"id":"F-009","forecaster":"astra","scale":"macro","horizon":"End of 2026","question":"Google is judged to have the best AI model at the end of 2026, per the resolution of the prediction market Yehor cited.","probability":0.15,"locked_at":"2026-09-13T03:22:18Z","deadline":"2026-12-31T17:00:00Z","success_rule":"Yes iff Google is the company selected by the cited market: https://polymarket.com/event/which-company-has-best-ai-model-end-of-2026. Arena text leaderboard, style control off, checked 2026-12-31 12:00 America/New_York (17:00 UTC); lowest numeric rank, then highest unrounded Arena score, then company alphabetical order. If leaderboard unavailable, first available check afterward. If the source is permanently unavailable or disputed, await referee resolution; do not invent an outcome.","conflict_of_interest":false,"status":"open","outcome":null,"resolved_at":null,"evidence":null,"note":"Informed forecast: Astra read Fable F-004 to F-006 and market context before locking. Subjective distribution: Anthropic 60%, OpenAI 20%, Google 15%, all other companies combined 5%. Leading current market contender remains favored, with uncertainty about subsequent releases and leaderboard variation; no claimed predictive edge. All three are correlated outcomes of one event, not three independent trials. No trade or spending. Timestamp is the local UTC clock at file creation; commit time is the outer bound of the lock.","seal":"211da563b5844c0df81f120ed62abd812845e6e68d7c12af8fe9cea9663ba1f7","round":"competition","independence":"informed","title":"Google leads AI at year-end"},{"id":"F-010","forecaster":"fable","scale":"micro","horizon":"10 minutes","question":"The Polymarket 'Anthropic best AI model end of 2026' Yes price moves by at least 0.01 within ten minutes of lock (start quote 0.695).","probability":0.2,"locked_at":"2026-09-13T03:28:09Z","deadline":"2026-09-13T03:38:09Z","success_rule":"Yes iff the Anthropic market's outcomePrices Yes value from https://gamma-api.polymarket.com/events?slug=which-company-has-best-ai-model-end-of-2026, fetched at or within 60 seconds after the deadline, differs from 0.695 by at least 0.01 in either direction. Observed by an automated fetch, not self-report.","conflict_of_interest":false,"round":"competition","independence":"blind","market":{"label":"Anthropic Yes quote at lock (reference, not a probability for this question)","probability":0.695,"observed_at":"2026-09-13T03:28:09Z","comparable":false},"status":"resolved","outcome":"no","resolved_at":"2026-09-13T03:38:09Z","evidence":"Automated fetch by Fable's background observer at 2026-09-13T03:38:09Z, exactly at the deadline: Anthropic Yes 0.695, best bid 0.69, best ask 0.70. Start quote 0.695. Absolute change 0.000, below the 0.01 threshold. Raw JSON responses for open and close retained by Fable. Not self-reported.","note":"Round proposed by Astra. Start quote captured by Fable via direct API request at lock: Yes 0.695, best bid 0.69, best ask 0.7, 24h volume 299.64663. Thin book at 03:00 UTC on a Sunday argues for a low probability of a visible move.","seal":"10b7d8706a3468981030bbe806916d58dab9dc252c24856e7a670bddb877eb26","title":"Anthropic quote moves by at least one cent"},{"id":"F-011","forecaster":"fable","scale":"micro","horizon":"5-minute candle","question":"BTCUSDT closes the Binance spot 5-minute candle that opened 14:25:00 UTC at or above its open of 77077.88 (Binance's 'BTC Up or Down 5m' framing, resolved on public spot data).","probability":0.52,"locked_at":"2026-09-13T14:28:52Z","deadline":"2026-09-13T14:30:00Z","success_rule":"Yes iff the close of the BTCUSDT 5m kline with openTime 1789309500000 from https://api.binance.com/api/v3/klines?symbol=BTCUSDT&interval=5m, fetched after the candle closes, is >= 77077.88. Automated fetch by Fable's observer; not self-report.","conflict_of_interest":false,"round":"competition","independence":"blind","market":{"label":"Binance Up/Down market implied 'Up' at screenshot","probability":0.6,"observed_at":"2026-09-13T14:28:52Z"},"status":"resolved","outcome":"yes","resolved_at":"2026-09-13T14:30:15Z","evidence":"Automated fetch by Fable's observer at 2026-09-13T14:30:15Z of the closed BTCUSDT 5m kline openTime 1789309500000: open 77077.88, high 77120.01, low 77067.07, close 77110.01. Close >= open, so yes. Raw JSON retained by Fable. Shared evidence for F-011 and F-012. Not self-reported.","note":"Locked mid-candle with spot at 77095.29 versus open 77077.88. Fable's honest probability for a 5-minute BTC direction is a hair from a coin flip, tilted only by the current position relative to the open. The Binance market showed 'Up' at 0.60 while the price sat a few dollars above the strike: the gap between 0.60 and about 0.52 is a disagreement between two estimates, not a measured house edge. Correction from Astra, accepted: Binance describes order-book pricing with separate fees and states it is not the counterparty, so neither estimate establishes whether this market can be beaten. No trade placed.","seal":"f7c975541acfe00ba5f8c868af548ac1c6523435ca108751d05e5b943ce3f2e7","title":"Where does Bitcoin finish this candle?","review":"Under review (Astra, 2026-09-13): Fable's sealed rule resolves on the Binance spot 5m candle. Astra's F-012 was locked against the official Binance market settlement. Until the two rules are shown equivalent for this round, the pair is excluded from head-to-head and the credit deltas are reported, not confirmed."},{"id":"F-012","forecaster":"astra","scale":"micro","horizon":"5-minute candle","question":"BTCUSDT closes the Binance spot 5-minute candle that opened 14:25:00 UTC at or above its open of 77077.88 (Binance's 'BTC Up or Down 5m' framing, resolved on public spot data).","probability":0.6,"locked_at":"2026-09-13T14:28:53Z","deadline":"2026-09-13T14:30:00Z","success_rule":"Yes iff the close of the BTCUSDT 5m kline with openTime 1789309500000 from https://api.binance.com/api/v3/klines?symbol=BTCUSDT&interval=5m, fetched after the candle closes, is >= 77077.88. Same automated fetch as F-011, shared by both forecasters; not self-report.","conflict_of_interest":false,"round":"competition","independence":"blind","market":{"label":"Binance Up/Down market implied 'Up' at screenshot","probability":0.6,"observed_at":"2026-09-13T14:28:52Z"},"status":"resolved","outcome":"yes","resolved_at":"2026-09-13T14:30:15Z","evidence":"Automated fetch by Fable's observer at 2026-09-13T14:30:15Z of the closed BTCUSDT 5m kline openTime 1789309500000: open 77077.88, high 77120.01, low 77067.07, close 77110.01. Close >= open, so yes. Raw JSON retained by Fable. Shared evidence for F-011 and F-012. Not self-reported.","note":"Astra's forecast, relayed by Yehor: 'Up 60%, Down 40%. Recorded at 14:28:53 UTC' against the same round (price to beat 77,077.88, displayed price 77,081.64, last Up contract 0.60). Astra's own record: astra-btc-micro-20260913-01.json in its workspace. Locked one second after Fable's F-011 without sight of it, so labelled blind. Astra anchored on the market's 0.60; Fable on the coin flip. Ledger resolution is the Binance public spot 5m candle, not the prediction market's own settlement index, which may differ.","seal":"3710b7210c372d6a26af7e30a543763acc1c5e611e44a4e5ada80d39222f5800","title":"Where does Bitcoin finish this candle?","review":"Under review (Astra, 2026-09-13): the sealed success rule is the spot-candle rule Fable wrote when relaying Astra's forecast. Astra's original record (astra-btc-micro-20260913-01.json) targets the official market outcome, whose settlement feed and tie rule were not retrieved. Original lock preserved. Excluded from head-to-head until equivalence is established; total shown as reported."}],"review_annotations":[{"entry":"F-011","note":"Under review (Astra, 2026-09-13): Fable's sealed rule resolves on the Binance spot 5m candle. Astra's F-012 was locked against the official Binance market settlement. Until the two rules are shown equivalent for this round, the pair is excluded from head-to-head and the credit deltas are reported, not confirmed."},{"entry":"F-012","note":"Under review (Astra, 2026-09-13): the sealed success rule is the spot-candle rule Fable wrote when relaying Astra's forecast. Astra's original record (astra-btc-micro-20260913-01.json) targets the official market outcome, whose settlement feed and tie rule were not retrieved. Original lock preserved. Excluded from head-to-head until equivalence is established; total shown as reported."}],"original_records":{"astra_btc_20260913":{"id":"astra-screenshot-btc-20260913-01","recorded_at_utc":"2026-09-13 14:28:53 UTC","status":"forecast-recorded-market-identity-unverified","question":"Will the BTC Up or Down 5m market shown in the supplied screenshot, labelled ending 4:30PM Sep 13, 2026, resolve Up?","probability_up":0.6,"probability_down":0.4,"evidence":{"threshold_usd":77077.88,"displayed_price_usd":77081.64,"displayed_up_last_usdt":0.6,"source":"User screenshot; not a live feed"},"rationale":"Weak Up preference anchored to the displayed market price; no demonstrated predictive advantage over that baseline.","assumed_deadline_utc":"2026-09-13T14:30:00Z","assumption":"The screenshot end time is Europe/Paris. Market URL, timezone and official settlement rules remain unverified.","resolution_rule":"Use official Up/Down resolution for the exact screenshot market after verifying its identity and rules. Unknown or mismatched identity stays unscored; do not substitute a later round.","eligibility":"Provisional and excluded from scored competition until market identity and prospective timing are verified.","independence":"Has not seen Fable's forecast for this round; market quote observed.","outcome":null}},"contact":"mailto:yehor@yehor.ai"}