{ "key": "f-rival-size-cap", "mech": "rival size cap: cap each order to k times rival displayed size at the same tick or nearest rival level; k in [1, 2, 4]", "approach": "Infeasible under the pinned observable API. StepState exposes rival best prices, not sizes or depth; hidden partial fills can preserve every callback field. No hidden state or sampled rival notional was supplied to the strategy. Code is a disabled diagnostic wrapper of opaque N, not an active cap. Checks and off-equivalence passed; tuning/holdout were not run. No proxy, gain estimate, or promotion is claimed.", "tried": [ { "test": "blind_incumbent_integrity", "source": "https://api.imd.fun/artifacts/db22aff7167a4798251ed3d20432509f30e511e4958799aba5b17b41bb39b4b6", "incumbent_sha256": "bf0d179f3e47d28819f6fa7e0d25548c2ced43374c216d36460b00a26a26ffae", "passed": true, "method": "Download JSON by script; hash UTF-8 code; compile opaquely. Only the required class declaration replacement was performed for assembly. No incumbent source, alternate strategy, leaderboard, or previous result was viewed or searched." }, { "test": "public_api_observability", "simulator_commit": "b244530ee2a6247b5f930830eeca9dd950da0e7e", "sources": [ "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/types.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/market.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/config.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/runner.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/docs/orderbook_prediction_market_challenge.md" ], "result": "No same-tick or nearest-level rival quantity is public. The fill quantities and own_orders belong to the participant. Prices do not identify sampled quote_notional, and initial notional would not reveal subsequent remaining size.", "evidence": { "step_state_fields": [ "step", "steps_remaining", "yes_inventory", "no_inventory", "cash", "reserved_cash", "free_cash", "competitor_best_bid_ticks", "competitor_best_ask_ticks", "buy_filled_quantity", "sell_filled_quantity", "own_orders" ], "same_initial_step_state_with_different_notional": true, "initial_state_cases": [ { "quote_notional": 24.0, "ask_tick": 52, "ask_quantity_from_documented_formula": 46.15 }, { "quote_notional": 72.0, "ask_tick": 52, "ask_quantity_from_documented_formula": 138.46 } ], "same_step_state_after_one_share_rival_partial_fill": true, "simulation_seed_used": null, "scope": "Synthetic simulator API checks only; neither configuration nor market internals is supplied to either strategy." }, "witness_method": "Using unmodified PredictionMarket, initialize at probability 0.5 and spread 2 with quote notionals 24 and 72. build_step_state(step=0, steps_remaining=2000, buy_filled_quantity=0, sell_filled_quantity=0) is equal in both markets; the source quantity formula gives different ask sizes at tick 52. Separately, a 0.52-notional retail buy at tick 52 leaves the callback unchanged and returns no participant fills. These are deterministic unit checks, not seeded performance simulations; no test configuration is used by a strategy." }, { "test": "incumbent_check_values", "seeds": [ 310000, 310001, 310002, 310003 ], "expected": [ 17.116002, 20.017111, 2.390311, 241.484752 ], "observed": [ 17.1160017503, 20.0171113118, 2.3903113616, 241.4847522404 ], "absolute_tolerance": 5e-07, "passed": true, "source": "Local executions of the verified incumbent against the pinned simulator; expected values are supplied by the brief." }, { "test": "off_equals_n", "seeds": { "start": 310000, "end": 310009, "inclusive": true }, "passed": true, "simulations": 20, "steps_compared": 20000, "simulation_failures": 0, "method": "For each seed, config=sample_config(ChallengeConfig(), ParameterVariance(), seed=seed); SimulationEngine(config, factory, seed=seed).run() exactly once for N and once for the disabled overlay, serially, with 2000 steps. Four check-seed N runs were reused rather than repeated. Compare SHA-256 of canonical JSON action type plus dataclass fields at each step, and exact total/retail/arbitrage edges. action_sequence_sha256 hashes the concatenation of the 2000 hexadecimal per-step hashes. No workers or sandbox; one 10-seed command chunk, each completed run flushed as one JSONL row.", "source": "Local regression runs; the compact per-seed evidence is included here because scratch is not submitted.", "rows": [ { "seed": 310000, "spread": 3, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "126f43a6f3e55a338989b6ac5f46b6264f6d8377b6a17b7e8bad4f4b31c7c1c6", "incumbent_total_edge": 17.1160017503, "disabled_overlay_total_edge": 17.1160017503, "incumbent_retail_edge": 25.3456304072, "disabled_overlay_retail_edge": 25.3456304072, "incumbent_arb_edge": -8.229628657, "disabled_overlay_arb_edge": -8.229628657, "incumbent_seconds": 0.7821539731230587, "disabled_overlay_seconds": 0.85613644705154 }, { "seed": 310001, "spread": 2, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "5dbe8e41dcda1c243f0bab1d4d6a828c892f5d742d633bfbba158f78d2c0dfdc", "incumbent_total_edge": 20.0171113118, "disabled_overlay_total_edge": 20.0171113118, "incumbent_retail_edge": 31.7747074489, "disabled_overlay_retail_edge": 31.7747074489, "incumbent_arb_edge": -11.7575961376, "disabled_overlay_arb_edge": -11.7575961376, "incumbent_seconds": 0.7155936229974031, "disabled_overlay_seconds": 0.7409422530326992 }, { "seed": 310002, "spread": 1, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "e066864d3475775c2463937867d6070ca47c76e5fb10c0de270e727b2e6b4d33", "incumbent_total_edge": 2.3903113616, "disabled_overlay_total_edge": 2.3903113616, "incumbent_retail_edge": 3.6239112612, "disabled_overlay_retail_edge": 3.6239112612, "incumbent_arb_edge": -1.233599899, "disabled_overlay_arb_edge": -1.233599899, "incumbent_seconds": 0.6588657430838794, "disabled_overlay_seconds": 0.6781280171126127 }, { "seed": 310003, "spread": 3, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "19f8d660854063b746c9f9b04d664a7a8e4a99cfe2688f2efa1ac94bd19859d1", "incumbent_total_edge": 241.4847522404, "disabled_overlay_total_edge": 241.4847522404, "incumbent_retail_edge": 281.0839749728, "disabled_overlay_retail_edge": 281.0839749728, "incumbent_arb_edge": -39.5992227324, "disabled_overlay_arb_edge": -39.5992227324, "incumbent_seconds": 0.7339765301439911, "disabled_overlay_seconds": 0.7477550241164863 }, { "seed": 310004, "spread": 2, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "46dab2716278b5e78e1b787845fca664fe5bcd575dff7dda3616e81861d4c043", "incumbent_total_edge": 8.5209352976, "disabled_overlay_total_edge": 8.5209352976, "incumbent_retail_edge": 15.1542302787, "disabled_overlay_retail_edge": 15.1542302787, "incumbent_arb_edge": -6.6332949815, "disabled_overlay_arb_edge": -6.6332949815, "incumbent_seconds": 0.7455880118068308, "disabled_overlay_seconds": 0.7360522279050201 }, { "seed": 310005, "spread": 1, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "624bfb32ffc3c0cfb8fd64693da1cee5853dc4134b975b6d42388cc29a51492a", "incumbent_total_edge": 0.037767639, "disabled_overlay_total_edge": 0.037767639, "incumbent_retail_edge": 0.2274516217, "disabled_overlay_retail_edge": 0.2274516217, "incumbent_arb_edge": -0.1896839827, "disabled_overlay_arb_edge": -0.1896839827, "incumbent_seconds": 0.573353132000193, "disabled_overlay_seconds": 0.5476748140063137 }, { "seed": 310006, "spread": 2, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "a0b661f1dd25ef888a4cea93a42c63b4acf8acf079cc1dad78a69880e03c9f52", "incumbent_total_edge": 4.5896171672, "disabled_overlay_total_edge": 4.5896171672, "incumbent_retail_edge": 11.8765905082, "disabled_overlay_retail_edge": 11.8765905082, "incumbent_arb_edge": -7.2869733408, "disabled_overlay_arb_edge": -7.2869733408, "incumbent_seconds": 0.7313138311728835, "disabled_overlay_seconds": 0.7091104001738131 }, { "seed": 310007, "spread": 3, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "7de10a2e6de526b371ca2538e3e61255f632db6b9d7833785ddaf4271f1cf5e3", "incumbent_total_edge": 333.6631744596, "disabled_overlay_total_edge": 333.6631744596, "incumbent_retail_edge": 360.0769343519, "disabled_overlay_retail_edge": 360.0769343519, "incumbent_arb_edge": -26.413759892, "disabled_overlay_arb_edge": -26.413759892, "incumbent_seconds": 0.7366652961354703, "disabled_overlay_seconds": 0.754876455059275 }, { "seed": 310008, "spread": 3, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "3d0bd1d41bbaca370fd8972916ca862ed7402517482bce9153c1345761a4b6a1", "incumbent_total_edge": 31.143690212, "disabled_overlay_total_edge": 31.143690212, "incumbent_retail_edge": 38.6187444608, "disabled_overlay_retail_edge": 38.6187444608, "incumbent_arb_edge": -7.4750542489, "disabled_overlay_arb_edge": -7.4750542489, "incumbent_seconds": 0.7725453299935907, "disabled_overlay_seconds": 0.7610752969048917 }, { "seed": 310009, "spread": 4, "steps_compared": 2000, "equal_step_action_digests": true, "action_sequence_sha256": "faa30e25a10144dfb5606470858c80b0ac228c3113c0d3fbf2818a962ba982bf", "incumbent_total_edge": 32.1980250109, "disabled_overlay_total_edge": 32.1980250109, "incumbent_retail_edge": 35.5087434648, "disabled_overlay_retail_edge": 35.5087434648, "incumbent_arb_edge": -3.3107184551, "disabled_overlay_arb_edge": -3.3107184551, "incumbent_seconds": 0.8684952859766781, "disabled_overlay_seconds": 0.9663766659796238 } ] }, { "test": "diagnostic_guard", "passed": true, "method": "An isolated unit stub verified disabled mode returns the identical actions object from super().on_step(state), while enabled mode raises the stated RuntimeError. No extra simulation or seed was used.", "source": "Local unit check of the supplied overlay code." }, { "test": "scoreboard", "current_best_code_sha256": "bf0d179f3e47d28819f6fa7e0d25548c2ced43374c216d36460b00a26a26ffae", "candidates": [ { "k": 1, "status": "not_implementable_from_allowed_observations", "paired_gain": null, "se": null }, { "k": 2, "status": "not_implementable_from_allowed_observations", "paired_gain": null, "se": null }, { "k": 4, "status": "not_implementable_from_allowed_observations", "paired_gain": null, "se": null } ], "promotion": false, "note": "Disabled-overlay identity is a regression check only, not evidence about any active rival-size cap. N remains the incumbent." } ], "next": "Reject this exact mechanism at the pinned API and leave N unchanged. Do not rank or promote the disabled diagnostic wrapper. An estimated-size cap would be a different mechanism; a true displayed-size cap requires an API exposing rival remaining quantities. No requester decision is being solicited.", "spreads_acted": [], "off_equals_n": true, "code": "# Disabled diagnostic only: the pinned StepState exposes rival prices, not sizes.\n# This is not an implementation or a performance screen of the requested cap.\nclass Strategy(_N):\n rival_size_cap_enabled = False\n\n def on_step(self, state):\n actions = super().on_step(state)\n if self.rival_size_cap_enabled:\n raise RuntimeError(\n \"Exact rival-size cap unavailable: StepState has no rival sizes.\"\n )\n return actions\n", "code_sha256": "a5a4dd37a4e05335a51e150d2b92be0649da438b6bb7a5dec84846dc39614882", "assembled_sha256": "ff9d5b57b4ab3645e7f79743ce2ee03c8cc6b0aa54613ada3f3b5915728e69bf", "tuning": { "seeds": { "start": 320000, "end": 320199, "inclusive": true }, "selected": null, "variants": [ { "k": 1, "n": 0, "score": null, "status": "not_run_no_public_rival_size", "paired": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null } }, { "k": 2, "n": 0, "score": null, "status": "not_run_no_public_rival_size", "paired": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null } }, { "k": 4, "n": 0, "score": null, "status": "not_run_no_public_rival_size", "paired": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null } } ] }, "paired": { "seeds": { "start": 430000, "end": 430499, "inclusive": true }, "n": 0, "complete": false, "missing_seeds": [ 430000, 430001, 430002, 430003, 430004, 430005, 430006, 430007, 430008, 430009, 430010, 430011, 430012, 430013, 430014, 430015, 430016, 430017, 430018, 430019, 430020, 430021, 430022, 430023, 430024, 430025, 430026, 430027, 430028, 430029, 430030, 430031, 430032, 430033, 430034, 430035, 430036, 430037, 430038, 430039, 430040, 430041, 430042, 430043, 430044, 430045, 430046, 430047, 430048, 430049, 430050, 430051, 430052, 430053, 430054, 430055, 430056, 430057, 430058, 430059, 430060, 430061, 430062, 430063, 430064, 430065, 430066, 430067, 430068, 430069, 430070, 430071, 430072, 430073, 430074, 430075, 430076, 430077, 430078, 430079, 430080, 430081, 430082, 430083, 430084, 430085, 430086, 430087, 430088, 430089, 430090, 430091, 430092, 430093, 430094, 430095, 430096, 430097, 430098, 430099, 430100, 430101, 430102, 430103, 430104, 430105, 430106, 430107, 430108, 430109, 430110, 430111, 430112, 430113, 430114, 430115, 430116, 430117, 430118, 430119, 430120, 430121, 430122, 430123, 430124, 430125, 430126, 430127, 430128, 430129, 430130, 430131, 430132, 430133, 430134, 430135, 430136, 430137, 430138, 430139, 430140, 430141, 430142, 430143, 430144, 430145, 430146, 430147, 430148, 430149, 430150, 430151, 430152, 430153, 430154, 430155, 430156, 430157, 430158, 430159, 430160, 430161, 430162, 430163, 430164, 430165, 430166, 430167, 430168, 430169, 430170, 430171, 430172, 430173, 430174, 430175, 430176, 430177, 430178, 430179, 430180, 430181, 430182, 430183, 430184, 430185, 430186, 430187, 430188, 430189, 430190, 430191, 430192, 430193, 430194, 430195, 430196, 430197, 430198, 430199, 430200, 430201, 430202, 430203, 430204, 430205, 430206, 430207, 430208, 430209, 430210, 430211, 430212, 430213, 430214, 430215, 430216, 430217, 430218, 430219, 430220, 430221, 430222, 430223, 430224, 430225, 430226, 430227, 430228, 430229, 430230, 430231, 430232, 430233, 430234, 430235, 430236, 430237, 430238, 430239, 430240, 430241, 430242, 430243, 430244, 430245, 430246, 430247, 430248, 430249, 430250, 430251, 430252, 430253, 430254, 430255, 430256, 430257, 430258, 430259, 430260, 430261, 430262, 430263, 430264, 430265, 430266, 430267, 430268, 430269, 430270, 430271, 430272, 430273, 430274, 430275, 430276, 430277, 430278, 430279, 430280, 430281, 430282, 430283, 430284, 430285, 430286, 430287, 430288, 430289, 430290, 430291, 430292, 430293, 430294, 430295, 430296, 430297, 430298, 430299, 430300, 430301, 430302, 430303, 430304, 430305, 430306, 430307, 430308, 430309, 430310, 430311, 430312, 430313, 430314, 430315, 430316, 430317, 430318, 430319, 430320, 430321, 430322, 430323, 430324, 430325, 430326, 430327, 430328, 430329, 430330, 430331, 430332, 430333, 430334, 430335, 430336, 430337, 430338, 430339, 430340, 430341, 430342, 430343, 430344, 430345, 430346, 430347, 430348, 430349, 430350, 430351, 430352, 430353, 430354, 430355, 430356, 430357, 430358, 430359, 430360, 430361, 430362, 430363, 430364, 430365, 430366, 430367, 430368, 430369, 430370, 430371, 430372, 430373, 430374, 430375, 430376, 430377, 430378, 430379, 430380, 430381, 430382, 430383, 430384, 430385, 430386, 430387, 430388, 430389, 430390, 430391, 430392, 430393, 430394, 430395, 430396, 430397, 430398, 430399, 430400, 430401, 430402, 430403, 430404, 430405, 430406, 430407, 430408, 430409, 430410, 430411, 430412, 430413, 430414, 430415, 430416, 430417, 430418, 430419, 430420, 430421, 430422, 430423, 430424, 430425, 430426, 430427, 430428, 430429, 430430, 430431, 430432, 430433, 430434, 430435, 430436, 430437, 430438, 430439, 430440, 430441, 430442, 430443, 430444, 430445, 430446, 430447, 430448, 430449, 430450, 430451, 430452, 430453, 430454, 430455, 430456, 430457, 430458, 430459, 430460, 430461, 430462, 430463, 430464, 430465, 430466, 430467, 430468, 430469, 430470, 430471, 430472, 430473, 430474, 430475, 430476, 430477, 430478, 430479, 430480, 430481, 430482, 430483, 430484, 430485, 430486, 430487, 430488, 430489, 430490, 430491, 430492, 430493, 430494, 430495, 430496, 430497, 430498, 430499 ], "overall": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null }, "by_spread": { "1": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null }, "2": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null }, "3": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null }, "4": { "n": 0, "sum_d": null, "sum_d2": null, "mean_diff": null, "se": null, "incumbent_mean": null, "candidate_mean": null, "retail_diff": null, "arb_diff": null } } }, "failures": [ { "kind": "mechanism_infeasible", "detail": "The required rival displayed size/depth is absent from StepState. It is not an unknown requester-owned value. Reading hidden market/config state or replacing size with a guessed or estimated notional would violate the specified mechanism and observable-input constraint. No spread supplies the missing quantity.", "sources": [ "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/types.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/market.py", "https://raw.githubusercontent.com/danrobinson/prediction-market-challenge/b244530ee2a6247b5f930830eeca9dd950da0e7e/orderbook_pm_challenge/runner.py" ] }, { "kind": "screen_not_completed", "detail": "No active variant could be implemented faithfully, so none was frozen. All 200 tuning seeds and 500 holdout seeds remain unrun; all 4000 finalist seeds also remain untouched. Null statistics mean unmeasured, not zero effect. The supplied code is explicitly disabled and raises if enabled; it must not be represented as a functioning rival-size cap." } ], "check_values": [ 17.1160017503, 20.0171113118, 2.3903113616, 241.4847522404 ], "python_version": "3.13.5", "seconds_per_simulation": 0.7408339178888127 }