{ "raw_dir": "data/raw", "max_files": 6, "datasets": [ { "id": "autocast", "file_count": 1, "total_bytes": 2016865, "sampled_files": [ { "path": "data/raw/autocast/repo/competition/autocast_competition_test_set.json", "format": "json", "bytes": 2016865, "rows": null, "columns": [] } ] }, { "id": "closed_polymarket_2025h1", "file_count": 1, "total_bytes": 2673120, "sampled_files": [ { "path": "data/raw/closed_polymarket_2025h1/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 2673120, "rows": 31627, "columns": [ "condition_id", "market_slug", "end_date_iso", "category", "minimum_tick_size", "minimum_order_size", "liquidity", "volume" ] } ] }, { "id": "forecast_snapshots_kalshi", "file_count": 3, "total_bytes": 13107576, "sampled_files": [ { "path": "data/raw/forecast_snapshots_kalshi/config.json", "format": "json", "bytes": 347, "rows": null, "columns": [] }, { "path": "data/raw/forecast_snapshots_kalshi/snapshot_dataset.csv", "format": "csv", "bytes": 12614878, "rows": null, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "model_pred_now", "outcomes" ] }, { "path": "data/raw/forecast_snapshots_kalshi/snapshot_dataset.parquet", "format": "parquet", "bytes": 492351, "rows": 20259, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "model_pred_now", "outcomes" ] } ] }, { "id": "forecast_snapshots_metaculus_large", "file_count": 3, "total_bytes": 6188957, "sampled_files": [ { "path": "data/raw/forecast_snapshots_metaculus_large/config.json", "format": "json", "bytes": 339, "rows": null, "columns": [] }, { "path": "data/raw/forecast_snapshots_metaculus_large/snapshot_dataset.csv", "format": "csv", "bytes": 5653170, "rows": null, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "forecaster_count_now", "range_min", "range_max", "zero_point", "open_lower_bound", "open_upper_bound", "model_pred_now", "outcomes" ] }, { "path": "data/raw/forecast_snapshots_metaculus_large/snapshot_dataset.parquet", "format": "parquet", "bytes": 535448, "rows": 1998, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "forecaster_count_now", "range_min", "range_max", "zero_point", "open_lower_bound", "open_upper_bound", "model_pred_now", "outcomes" ] } ] }, { "id": "forecast_snapshots_metaculus_small", "file_count": 3, "total_bytes": 605024, "sampled_files": [ { "path": "data/raw/forecast_snapshots_metaculus_small/config.json", "format": "json", "bytes": 383, "rows": null, "columns": [] }, { "path": "data/raw/forecast_snapshots_metaculus_small/snapshot_dataset.csv", "format": "csv", "bytes": 447601, "rows": null, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "forecaster_count_now", "range_min", "range_max", "zero_point", "open_lower_bound", "open_upper_bound", "model_pred_now", "outcomes" ] }, { "path": "data/raw/forecast_snapshots_metaculus_small/snapshot_dataset.parquet", "format": "parquet", "bytes": 157040, "rows": 154, "columns": [ "market_source", "market_id", "question", "question_type", "unit", "url", "description", "resolution_criteria", "categories", "tags", "snapshot_time", "snapshot_datetime", "close_time", "close_datetime", "days_until_close", "resolution_time", "community_pred_now", "community_pred_1day", "community_pred_3day", "community_pred_1week", "community_pred_2week", "community_pred_1month", "pred_1week_is_resolution", "pred_1month_is_resolution", "resolution", "resolution_numeric", "forecaster_count_now", "range_min", "range_max", "zero_point", "open_lower_bound", "open_upper_bound", "model_pred_now", "outcomes" ] } ] }, { "id": "forecastbench", "file_count": 41, "total_bytes": 121849554, "sampled_files": [ { "path": "data/raw/forecastbench/datasets/forecast_sets/2024-07-21/2024-07-21.ForecastBench.human_public_individual.json", "format": "json", "bytes": 23526935, "rows": null, "columns": [] }, { "path": "data/raw/forecastbench/datasets/forecast_sets/2024-07-21/2024-07-21.ForecastBench.human_super_individual.json", "format": "json", "bytes": 4595808, "rows": null, "columns": [] }, { "path": "data/raw/forecastbench/datasets/question_sets/2024-07-21-human.json", "format": "json", "bytes": 553367, "rows": null, "columns": [] }, { "path": "data/raw/forecastbench/datasets/question_sets/2024-07-21-llm.json", "format": "json", "bytes": 4831631, "rows": null, "columns": [] }, { "path": "data/raw/forecastbench/datasets/question_sets/2025-03-02-llm.json", "format": "json", "bytes": 4762520, "rows": null, "columns": [] }, { "path": "data/raw/forecastbench/datasets/question_sets/2025-03-16-llm.json", "format": "json", "bytes": 4773527, "rows": null, "columns": [] } ] }, { "id": "futurex_online", "file_count": 1, "total_bytes": 23727, "sampled_files": [ { "path": "data/raw/futurex_online/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 23727, "rows": 76, "columns": [ "id", "prompt", "end_time", "level", "en_title" ] } ] }, { "id": "futurex_past", "file_count": 1, "total_bytes": 249971, "sampled_files": [ { "path": "data/raw/futurex_past/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 249971, "rows": 1129, "columns": [ "id", "prompt", "end_time", "level", "title", "ground_truth" ] } ] }, { "id": "halawi_llm_forecasting", "file_count": 0, "total_bytes": 0, "sampled_files": [] }, { "id": "ir_event_forecasting_sample", "file_count": 2, "total_bytes": 87000, "sampled_files": [ { "path": "data/raw/ir_event_forecasting_sample/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 58712, "rows": 20, "columns": [ "original_data", "original_question", "original_answer", "solution", "candidates", "reasoning_content", "question", "model_answer" ] }, { "path": "data/raw/ir_event_forecasting_sample/data/valid-00000-of-00001.parquet", "format": "parquet", "bytes": 28288, "rows": 4, "columns": [ "original_data", "original_question", "original_answer", "solution", "candidates", "reasoning_content", "question", "model_answer" ] } ] }, { "id": "kalshi_filtered", "file_count": 1, "total_bytes": 176406, "sampled_files": [ { "path": "data/raw/kalshi_filtered/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 176406, "rows": 1433, "columns": [ "cutoff_time", "week_id", "ticker", "event_ticker", "title", "subtitle", "category", "rules_primary", "price_at_cutoff", "last_price", "last_price_dollars", "yes_bid", "yes_ask", "no_bid", "no_ask", "volume", "volume_24h", "open_interest", "liquidity", "liquidity_dollars", "days_until_resolution", "days_since_open", "market_duration_days", "open_time", "expected_expiration_time", "market_type", "strike_type", "floor_strike", "result", "settlement_value" ] } ] }, { "id": "kalshi_markets", "file_count": 1, "total_bytes": 1432564, "sampled_files": [ { "path": "data/raw/kalshi_markets/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 1432564, "rows": 10016, "columns": [ "ticker", "event_ticker", "market_type", "title", "subtitle", "yes_sub_title", "no_sub_title", "open_time", "close_time", "expected_expiration_time", "expiration_time", "latest_expiration_time", "settlement_timer_seconds", "status", "response_price_units", "notional_value", "notional_value_dollars", "yes_bid", "yes_bid_dollars", "yes_ask", "yes_ask_dollars", "no_bid", "no_bid_dollars", "no_ask", "no_ask_dollars", "last_price", "last_price_dollars", "previous_yes_bid", "previous_yes_bid_dollars", "previous_yes_ask", "previous_yes_ask_dollars", "previous_price", "previous_price_dollars", "volume", "volume_24h", "liquidity", "liquidity_dollars", "open_interest", "result", "settlement_value", "settlement_value_dollars", "can_close_early", "expiration_value", "category", "risk_limit_cents", "strike_type", "custom_strike", "rules_primary", "rules_secondary", "early_close_condition", "tick_size", "floor_strike", "cap_strike" ] } ] }, { "id": "kalshi_prop_closes", "file_count": 22, "total_bytes": 31251392, "sampled_files": [ { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-10.jsonl.gz", "format": "jsonl", "bytes": 1033732, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] }, { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-11.jsonl.gz", "format": "jsonl", "bytes": 1064937, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] }, { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-12.jsonl.gz", "format": "jsonl", "bytes": 1403193, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] }, { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-13.jsonl.gz", "format": "jsonl", "bytes": 1659277, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] }, { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-14.jsonl.gz", "format": "jsonl", "bytes": 1537293, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] }, { "path": "data/raw/kalshi_prop_closes/prop_closes_2026-06-15.jsonl.gz", "format": "jsonl", "bytes": 1324247, "rows": null, "columns": [ "src", "sport", "league", "gid", "mid", "teams", "start", "cutoff", "type", "period", "units", "desc", "cat", "limit", "prices", "ts" ] } ] }, { "id": "kalshi_rfq_momentum", "file_count": 0, "total_bytes": 0, "sampled_files": [] }, { "id": "kalshi_trades_trevorjs", "file_count": 20, "total_bytes": 5685396710, "sampled_files": [ { "path": "data/raw/kalshi_trades_trevorjs/markets-0000.parquet", "format": "parquet", "bytes": 136002798, "rows": 5000000, "columns": [ "ticker", "event_ticker", "market_type", "title", "yes_sub_title", "no_sub_title", "status", "yes_bid", "yes_ask", "no_bid", "no_ask", "last_price", "volume", "volume_24h", "open_interest", "result", "created_time", "open_time", "close_time" ] }, { "path": "data/raw/kalshi_trades_trevorjs/markets-0001.parquet", "format": "parquet", "bytes": 364296885, "rows": 5000000, "columns": [ "ticker", "event_ticker", "market_type", "title", "yes_sub_title", "no_sub_title", "status", "yes_bid", "yes_ask", "no_bid", "no_ask", "last_price", "volume", "volume_24h", "open_interest", "result", "created_time", "open_time", "close_time" ] }, { "path": "data/raw/kalshi_trades_trevorjs/markets-0002.parquet", "format": "parquet", "bytes": 400851398, "rows": 5000000, "columns": [ "ticker", "event_ticker", "market_type", "title", "yes_sub_title", "no_sub_title", "status", "yes_bid", "yes_ask", "no_bid", "no_ask", "last_price", "volume", "volume_24h", "open_interest", "result", "created_time", "open_time", "close_time" ] }, { "path": "data/raw/kalshi_trades_trevorjs/markets-0003.parquet", "format": "parquet", "bytes": 212771767, "rows": 2464713, "columns": [ "ticker", "event_ticker", "market_type", "title", "yes_sub_title", "no_sub_title", "status", "yes_bid", "yes_ask", "no_bid", "no_ask", "last_price", "volume", "volume_24h", "open_interest", "result", "created_time", "open_time", "close_time" ] }, { "path": "data/raw/kalshi_trades_trevorjs/trades-0000.parquet", "format": "parquet", "bytes": 313703141, "rows": 10000000, "columns": [ "trade_id", "ticker", "count", "yes_price", "no_price", "taker_side", "created_time" ] }, { "path": "data/raw/kalshi_trades_trevorjs/trades-0001.parquet", "format": "parquet", "bytes": 288411075, "rows": 9999678, "columns": [ "trade_id", "ticker", "count", "yes_price", "no_price", "taker_side", "created_time" ] } ] }, { "id": "kalshi_trades_wmitch", "file_count": 2, "total_bytes": 276868855, "sampled_files": [ { "path": "data/raw/kalshi_trades_wmitch/data/train-00000-of-00002.parquet", "format": "parquet", "bytes": 138396419, "rows": 2538256, "columns": [ "trade_id", "ticker", "count", "created_time", "yes_price", "no_price", "taker_side", "market_ticker" ] }, { "path": "data/raw/kalshi_trades_wmitch/data/train-00001-of-00002.parquet", "format": "parquet", "bytes": 138472436, "rows": 2538255, "columns": [ "trade_id", "ticker", "count", "created_time", "yes_price", "no_price", "taker_side", "market_ticker" ] } ] }, { "id": "kalshibench_v1", "file_count": 1, "total_bytes": 162550, "sampled_files": [ { "path": "data/raw/kalshibench_v1/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 162550, "rows": 894, "columns": [ "id", "question", "description", "category", "close_time", "ground_truth", "market_probability", "series_ticker", "source" ] } ] }, { "id": "kalshibench_v2", "file_count": 1, "total_bytes": 202676, "sampled_files": [ { "path": "data/raw/kalshibench_v2/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 202676, "rows": 1531, "columns": [ "id", "question", "description", "category", "close_time", "ground_truth", "market_probability", "series_ticker", "source" ] } ] }, { "id": "metaculus_binary_chandak", "file_count": 1, "total_bytes": 3537445, "sampled_files": [ { "path": "data/raw/metaculus_binary_chandak/train/train-00000-of-00001.parquet", "format": "parquet", "bytes": 3537445, "rows": 4265, "columns": [ "date_resolve_at", "date_begin", "extracted_urls", "question_type", "url", "background", "resolution_criteria", "is_resolved", "date_close", "question", "data_source", "resolution", "nr_forecasters" ] } ] }, { "id": "metaculus_binary_jijivski", "file_count": 2, "total_bytes": 89795, "sampled_files": [ { "path": "data/raw/metaculus_binary_jijivski/metaculus_binary.json", "format": "json", "bytes": 0, "rows": null, "columns": [] }, { "path": "data/raw/metaculus_binary_jijivski/test.json", "format": "json", "bytes": 89795, "rows": null, "columns": [ "question", "possibilities", "label", "description", "created_time", "resolve_time" ] } ] }, { "id": "mirai", "file_count": 2, "total_bytes": 107011, "sampled_files": [ { "path": "data/raw/mirai/repo/examples/outputs_raw/gpt-4o_react_block.json", "format": "json", "bytes": 58033, "rows": null, "columns": [] }, { "path": "data/raw/mirai/repo/examples/outputs_raw/gpt-4o_react_func.json", "format": "json", "bytes": 48978, "rows": null, "columns": [] } ] }, { "id": "mlb_polymarket_kalshi_matched_sample", "file_count": 2, "total_bytes": 132839, "sampled_files": [ { "path": "data/raw/mlb_polymarket_kalshi_matched_sample/mlb_matched_sample_ARI-MIN_2026-06-21.csv", "format": "csv", "bytes": 110091, "rows": null, "columns": [ "ts", "date", "game", "team", "poly_bid", "poly_ask", "poly_mid", "kalshi_yes_bid", "kalshi_yes_ask", "kalshi_mid", "xvenue_spread", "winner", "won", "settled" ] }, { "path": "data/raw/mlb_polymarket_kalshi_matched_sample/mlb_matched_sample_ARI-MIN_2026-06-21.parquet", "format": "parquet", "bytes": 22748, "rows": 1204, "columns": [ "ts", "date", "game", "team", "poly_bid", "poly_ask", "poly_mid", "kalshi_yes_bid", "kalshi_yes_ask", "kalshi_mid", "xvenue_spread", "winner", "won", "settled" ] } ] }, { "id": "openforesight", "file_count": 8, "total_bytes": 477959595, "sampled_files": [ { "path": "data/raw/openforesight/data/aljazeera2026Q1-00000-of-00001.parquet", "format": "parquet", "bytes": 1362638, "rows": 330, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer", "answer_type", "url", "article_title", "article_description", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] }, { "path": "data/raw/openforesight/data/aljazeeraLate2025-00000-of-00001.parquet", "format": "parquet", "bytes": 4652896, "rows": 491, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer", "answer_type", "url", "article_title", "article_description", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] }, { "path": "data/raw/openforesight/data/skysports2025-00000-of-00001.parquet", "format": "parquet", "bytes": 6901245, "rows": 1788, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer_type", "answer", "url", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "article_description", "article_title", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] }, { "path": "data/raw/openforesight/data/test-00000-of-00001.parquet", "format": "parquet", "bytes": 2793065, "rows": 302, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer_type", "answer", "url", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "article_description", "article_title", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] }, { "path": "data/raw/openforesight/data/train-00000-of-00003.parquet", "format": "parquet", "bytes": 154156215, "rows": 17395, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer_type", "answer", "url", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "article_description", "article_title", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] }, { "path": "data/raw/openforesight/data/train-00001-of-00003.parquet", "format": "parquet", "bytes": 157010712, "rows": 17395, "columns": [ "qid", "question_title", "background", "resolution_criteria", "answer_type", "answer", "url", "article_maintext", "article_publish_date", "article_modify_date", "article_download_date", "article_description", "article_title", "data_source", "news_source", "resolution_date", "question_start_date", "prompt", "prompt_without_retrieval" ] } ] }, { "id": "polybench", "file_count": 0, "total_bytes": 0, "sampled_files": [] }, { "id": "polymarket_10000", "file_count": 1, "total_bytes": 4750512, "sampled_files": [ { "path": "data/raw/polymarket_10000/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 4750512, "rows": 10000, "columns": [ "enable_order_book", "active", "closed", "archived", "accepting_orders", "accepting_order_timestamp", "minimum_order_size", "minimum_tick_size", "condition_id", "question_id", "question", "description", "market_slug", "end_date_iso", "game_start_time", "seconds_delay", "fpmm", "maker_base_fee", "taker_base_fee", "notifications_enabled", "neg_risk", "neg_risk_market_id", "neg_risk_request_id", "icon", "image", "rewards", "is_50_50_outcome", "tokens", "tags" ] } ] }, { "id": "polymarket_5min_crypto_updown", "file_count": 14, "total_bytes": 725013472, "sampled_files": [ { "path": "data/raw/polymarket_5min_crypto_updown/bnb_markets.parquet", "format": "parquet", "bytes": 2994440, "rows": 12259, "columns": [ "condition_id", "event_id", "slug", "market_start", "market_end", "recorded_at", "token_up", "token_down", "volume", "liquidity", "outcome", "n_ticks" ] }, { "path": "data/raw/polymarket_5min_crypto_updown/bnb_ticks.parquet", "format": "parquet", "bytes": 76690643, "rows": 3677623, "columns": [ "condition_id", "t", "ts_utc", "bu", "au", "bd", "ad", "su", "sd", "sau", "sad", "du", "dd" ] }, { "path": "data/raw/polymarket_5min_crypto_updown/btc_markets.parquet", "format": "parquet", "bytes": 3921352, "rows": 15682, "columns": [ "condition_id", "event_id", "slug", "market_start", "market_end", "recorded_at", "token_up", "token_down", "volume", "liquidity", "outcome", "n_ticks" ] }, { "path": "data/raw/polymarket_5min_crypto_updown/btc_ticks.parquet", "format": "parquet", "bytes": 182475803, "rows": 4704518, "columns": [ "condition_id", "t", "ts_utc", "bu", "au", "bd", "ad", "su", "sd", "sau", "sad", "du", "dd" ] }, { "path": "data/raw/polymarket_5min_crypto_updown/doge_markets.parquet", "format": "parquet", "bytes": 2999540, "rows": 12259, "columns": [ "condition_id", "event_id", "slug", "market_start", "market_end", "recorded_at", "token_up", "token_down", "volume", "liquidity", "outcome", "n_ticks" ] }, { "path": "data/raw/polymarket_5min_crypto_updown/doge_ticks.parquet", "format": "parquet", "bytes": 80060676, "rows": 3677623, "columns": [ "condition_id", "t", "ts_utc", "bu", "au", "bd", "ad", "su", "sd", "sau", "sad", "du", "dd" ] } ] }, { "id": "polymarket_clean", "file_count": 1, "total_bytes": 81935, "sampled_files": [ { "path": "data/raw/polymarket_clean/data/train-00000-of-00001.parquet", "format": "parquet", "bytes": 81935, "rows": 1000, "columns": [ "id", "amount", "shares", "userId", "outcome", "dpmShares", "probAfter", "contractId", "probBefore", "createdTime" ] } ] }, { "id": "polymarket_dataset_bbasavar", "file_count": 1, "total_bytes": 94707271, "sampled_files": [ { "path": "data/raw/polymarket_dataset_bbasavar/fine_tune.jsonl", "format": "jsonl", "bytes": 94707271, "rows": null, "columns": [ "instruction", "input", "output" ] } ] }, { "id": "polymarket_kalshi_scoresync_sample", "file_count": 3, "total_bytes": 186960, "sampled_files": [ { "path": "data/raw/polymarket_kalshi_scoresync_sample/DATA_CARD.json", "format": "json", "bytes": 1595, "rows": null, "columns": [] }, { "path": "data/raw/polymarket_kalshi_scoresync_sample/kalshi_scoresync_PHI_at_TOR_2026-01-11.parquet", "format": "parquet", "bytes": 56948, "rows": 1844, "columns": [ "timestamp", "ticker", "title", "game_id", "home_team", "away_team", "home_score", "away_score", "score_diff", "period", "time_remaining", "game_state", "yes_bid", "yes_ask", "mid", "spread", "spread_cents", "yes_bid_size", "yes_ask_size", "min_size", "open_interest", "volume_24h", "liquidity_score", "tradable_now", "is_burst_mode", "datetime_utc" ] }, { "path": "data/raw/polymarket_kalshi_scoresync_sample/kalshi_scoresync_PHI_at_TOR_HIGHLIGHTS.csv", "format": "csv", "bytes": 128417, "rows": null, "columns": [ "datetime_utc", "period", "time_remaining", "game_state", "home_team", "away_team", "home_score", "away_score", "score_diff", "score_changed", "yes_bid", "yes_ask", "mid", "spread", "yes_bid_size", "yes_ask_size" ] } ] }, { "id": "polymarket_minute_parquet", "file_count": 18, "total_bytes": 1432129480, "sampled_files": [ { "path": "data/raw/polymarket_minute_parquet/data/7397d2df-6622-4860-8797-6803b5740470.parquet", "format": "parquet", "bytes": 8043, "rows": 342, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] }, { "path": "data/raw/polymarket_minute_parquet/data/train-00000-of-00017.parquet", "format": "parquet", "bytes": 44720136, "rows": 6008518, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] }, { "path": "data/raw/polymarket_minute_parquet/data/train-00001-of-00017.parquet", "format": "parquet", "bytes": 44566730, "rows": 6008517, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] }, { "path": "data/raw/polymarket_minute_parquet/data/train-00002-of-00017.parquet", "format": "parquet", "bytes": 89573575, "rows": 12017035, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] }, { "path": "data/raw/polymarket_minute_parquet/data/train-00003-of-00017.parquet", "format": "parquet", "bytes": 89352774, "rows": 12017035, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] }, { "path": "data/raw/polymarket_minute_parquet/data/train-00004-of-00017.parquet", "format": "parquet", "bytes": 89417491, "rows": 12017035, "columns": [ "timestamp", "price", "token_id", "side", "market_id", "event_id", "question" ] } ] }, { "id": "prophet", "file_count": 0, "total_bytes": 0, "sampled_files": [] }, { "id": "prophet_arena_100", "file_count": 1, "total_bytes": 2115113, "sampled_files": [ { "path": "data/raw/prophet_arena_100/subset_data_100.csv", "format": "csv", "bytes": 2115113, "rows": null, "columns": [ "event_ticker", "title", "category", "markets", "close_time", "market_outcome", "sources", "market_info", "snapshot_time", "submission_id", "submission_created_at" ] } ] }, { "id": "prophet_arena_1200", "file_count": 1, "total_bytes": 8988523, "sampled_files": [ { "path": "data/raw/prophet_arena_1200/subset_data_1200.csv", "format": "csv", "bytes": 8988523, "rows": null, "columns": [ "submission_id", "event_ticker", "title", "snapshot_time", "close_time", "market_data", "market_outcome", "category", "markets", "augmented_title", "rules", "sources" ] } ] } ] }