Output Explorer

Every prompt in the paper, and what each model wrote back.

Return exactly ten single-sentence facts as JSON. Quality was judged pairwise; here you see the raw outputs and whether the JSON parsed.

13 of 1,000 prompts

PAL · Q2 20252025-08-11 PARR · Q4 20252026-02-25 PRPO · Q2 20252025-08-14 CRNC · Q4 20252025-11-19 BEEP · Q4 20252026-03-02 SBCF · Q3 20252025-10-28 CLX · Q1 20262025-11-03 AYI · Q4 20252025-10-01 AN · Q2 20252025-07-25 XEL · Q1 20262026-04-30 XERS · Q4 20252026-03-02 ALRS · Q3 20252025-10-31 MDU · Q2 20252025-08-07

Nearby prompts. All 1,000 Earnings calls prompts

PromptCLX· Q1 2026 · call on2025-11-03· transcript 50,752 characters

Analyze the following earnings call transcript and extract the 10 most investor-relevant facts.

Each fact must:
- Be drawn only from the transcript (do not use any outside information).
- Be a single sentence capturing a specific, quantified insight relevant to investors.
- Avoid regurgitating the transcript verbatim; instead, synthesize and distill the information into investor-relevant facts.

Return only a JSON object with this exact structure (no markdown fences, no commentary):
{"facts": ["<fact 1>", "<fact 2>", ..., "<fact 10>"]}

The list must contain exactly 10 facts.

Transcript:
<transcript>
transcript redacted — the source calls are not publicly licensed
</transcript>

System prompt · identical for every setup

You are a financial analyst. You extract the most investor-relevant facts from earnings call transcripts to help investors anticipate the stock's reaction to the call.

Reference

No reference summary is published. Quality was judged pairwise by a separate model and is reported in aggregate on the main page.

Ours

10 facts · valid JSON

Operators expect Q2 organic sales growth to remain in negative low single digits due to U.S. retail consumption trends and approximately 100 basis points of headwinds from Q1 shipment timing.
The full-year outlook projects front-half organic sales growth in negative low single digits, shifting to positive low single digits in the back half driven by market share gains and innovation lapps.
ERP implementation disruptions caused negative 3.0 percentage points of impact in Q1, comprising favorable timing shifts offset by 3 percentage points of out-of-stock market share losses.
Management projects total input cost inflation for the year at $70 million, which is $20 million more favorable than prior estimates, partially offset by a stable tariff headwind of $40 million.
Price/mix is expected to contribute a headwind of approximately 1 percentage point for the full year, reflecting continued value-seeking consumer behavior and channel shifting.
The Erlang of innovation is expected to be a primary driver of demand in the back half, with new scent platforms for Glad, smaller Brita pitcher/filters, and lotion/butter innovations for Berts.
Private label share remains muted in aggregate, though specific vulnerability is noted in Brita filters where consumers are trading down to lower-priced alternatives and in Bleach.
Run-rate EPS analysis suggests adding back the impact of the ERP transition timing shift to current guidance to establish a base of approximately $5.95 for forward planning.
Trash and Cat Litter categories are experiencing higher-than-normal promotional activity and competitive intensity, prompting a strategy to accept short-term share losses to preserve long-term value.
Retailer destocking is not currently a material factor as Clorox has finished rebuilding channel inventories following the ERP-related supply disruptions in Q1.

Aux 2015

10 facts · valid JSON

<fact 1>
<fact 2>
<fact 3>
<fact 4>
<fact 5>
<fact 6>
<fact 7>
<fact 8>
<fact 9>
<fact 10>

PiT-FT 2015

Invalid JSONshown as written

<|assistant|>
<|assistant|>
<|assistant|>

The same 14-character fragment repeats 292 times until the token limit. Showing the first three.

ChronoGPT 2015

Invalid JSONshown as written


### Final Answer: