Demo 2 — Guiding generation

Evolutionary voice design, with the four ears as the fitness signal.

Perception becomes authorship when you put it in a loop. Our text-to-speech model is MOSS-TTS-Local-Transformer v1.5 (4.55B, 48 kHz, no reference recording required), which we fine-tuned on permissively-licensed speech with emotion annotations, for instruction following — so it takes a natural-language voice instruction and speaks a line in that voice. An autonomous coding agent then runs an evolutionary search over those instructions, using the four ears as the fitness signal. Nothing about a character’s identity is copied from a real actor: the voice is designed from words and selected by machine listening.

The loop, per character.

Population. 10 candidate instructions per generation. Generation 1 is authored (seeded from the character’s previous champion); generations 2–4 are produced by mutation of the winners.
Best-of-N generation. Each candidate is spoken 8× with stochastic sampling (a rare good take matters more than an average one).
Scoring & fitness. Every take is scored by all four ears. Scores are min–max normalized within a single scorer call, then combined:
reward = w_blend·blend + w_genu·genu + w_vn·char_VN + w_emo·char_EMO × WER-factor
where char_VN is a weighted mean over the character’s target VoiceNet dimensions (rewarding the “positive” dims and the absence of “negative” ones), char_EMO a weighted mean over its target emotions, and the WER-factor is an intelligibility gate from an ASR system (Parakeet v3): clean voices are penalised for garbled speech, while monster/scream voices are exempt (you don’t dock a dragon for not enunciating).
Selection & mutation. Top-2 winners carry over verbatim (elitism); the top-5 are mutated by appending an emphasis clause and swapping the affect-burst, rotating phrase banks each generation.
Finals. The cross-generation champions play off head-to-head in a single normalized call; the winner is then re-sampled 64× and its top-3 takes are the ones you hear below.

Because normalization is per-call, candidates are only comparable inside one call — hence champions are always chosen by same-call play-offs, never by averaging across calls.

Different ears for different characters. Crucially, each character defines its own fitness: its own set of positive/negative VoiceNet dimensions, its own target emotions, its own per-dimension weights, and its own intelligibility gate. A cartoon mouse up-weights pitch-range, register and brightness; a pain-scream up-weights arousal ×3.5 and switches the WER gate off; a grieving voice weights the Sadness emotion head ×3; gender is split simply by pushing the “perceived gender” dimension positive or negative. The same taxonomy, re-weighted, becomes 13 different objective functions.

The final grid — 13 designed characters

Each character is the winner of an independent evolutionary run (4 generations × 10 instructions, best-of-8 during search, a normalized play-off, then best-of-64 for the finals). You hear the top-3 of the final 64 takes; every number is produced by the four ears, and the “fitness target” line shows the character’s own objective.

Monsters & Creatures

🧟 Zombie

Winning instruction: “A pitiful half-dead zombie, utterly helpless and abandoned, whimpering and pleading, weak, trembling and vulnerable, forsaken and lost, delirious with fever and dull pain. A hollow groan from a sunken caved-in chest choking through a wet gurgling guttural throat, phlegmy rasp, decayed. Dark and dim, meek and powerless, no authority, no brightness, slurred and drained. (feeble whimper)”

Spoken line: “So... hungry... hnngh... help me... I can't... stop...”

① champion · reward 3.05 · char 0.80 · emo 0.55 · blend 7.2 · genu 1.7 · WER 0.11 · 8s

② runner-up · reward 2.81 · char 0.70 · emo 0.45 · blend 7.1 · genu 2.0 · WER 0.11 · 12s

③ third · reward 2.80 · char 0.70 · emo 0.45 · blend 7.1 · genu 2.0 · WER 0.11 · 12s

Loudest VoiceNet dims (champion): Vulnerability 4.5Perceived Gender 4.4Cognitive Load 4.3Respiration 4.0
Top emotions: Helplessness 3.2Intoxication/Altered States 2.1Fatigue/Exhaustion 2.0

This character’s fitness target: None

Character-fit across rounds: r1:0.693 → r3:0.809 → r4:– → r5:0.799

What the agent learned: Naming HELPLESSNESS/abandonment + pleading and moving the affect into the spoken text (pleading fragments like "help me... I can't... stop") lifted char_emo above the round-3 meek/powerless framing while keeping the hollow caved-in chest + wet gurgling throat core intact.

👹 Ork

Winning instruction: “An enormous brutish orc, his voice a deep chest-driven guttural bass, resonating from a massive barrel chest and gravelled throat, thick and rough, full and cavernous. Commanding, dominant and immovable, planting each word like a boot with crushing authority. Low, flat and narrow, never leaping in pitch. Boiling with hateful loathing, withering sneering contempt, cruel cold menace and dark triumph, zero brightness. Growled but every word lands. (guttural growl) High quality recording.”

Spoken line: “You should not have come here, little one. This is where your journey ends.”

① champion · reward 3.08 · char 0.67 · emo 0.93 · blend 2.7 · genu 1.0 · WER 0.00 · 7s

② runner-up · reward 2.67 · char 0.69 · emo 0.44 · blend 9.1 · genu 0.9 · WER 0.00 · 6s

③ third · reward 2.42 · char 0.69 · emo 0.44 · blend 9.1 · genu 0.9 · WER 0.00 · 6s

Loudest VoiceNet dims (champion): Storytelling Style 4.6Fullness 4.6Throat Resonance 4.6Chest Resonance 4.3
Top emotions: Malevolence/Malice 2.4Anger 2.3Contempt 1.9

This character’s fitness target: None

Character-fit across rounds: r1:0.336 → r3:0.531 → r4:– → r5:0.67

What the agent learned: Refined the round-3 champion (o_deepchest) toward HATEFUL menace: 'Boiling with hateful loathing, withering sneering contempt, cruel cold menace and dark triumph' replaced the plainer 'Seething hatred and sneering contempt, dark triumphant menace'. This lifted char_emo (Anger/Malevolence/Contempt/Triumph) to 0.93 on the best-of-64 top take while holding invWER at 1.0.

👺 Goblin

Winning instruction: “A truly evil, malevolent little goblin, extremely nasal, pinched and reedy, buzzing and grating high through the nose. Cold sadistic cruelty in every hissing word, wicked, vicious and remorseless, menacing and threatening, gloating over pain, pure malice to the core. The whiny pitch cracks and skitters higher and shriller with wicked glee, snickering and jeering. A weak cowardly nobody, no authority. No chest, no warmth, no fullness. Nasty but every word lands. (malicious hiss) High quality recording.”

Spoken line: “Heh heh, what have we here? A lost little traveler with shiny pockets?”

① champion · reward 2.45 · char 0.56 · emo 0.57 · blend 3.3 · genu 1.9 · WER 0.15 · 12s

② runner-up · reward 2.34 · char 0.56 · emo 0.37 · blend 2.6 · genu 2.0 · WER 0.23 · 7s

③ third · reward 2.22 · char 0.45 · emo 0.22 · blend 7.2 · genu 1.5 · WER 0.15 · 8s

Loudest VoiceNet dims (champion): Casual Style 5.4Storytelling Style 4.7Playful Style 4.4Vulnerability 4.3
Top emotions: Malevolence/Malice 1.4Contempt 0.8Teasing 0.8

This character’s fitness target: None

Character-fit across rounds: r1:0.584 → r3:0.737 → r4:0.476 → r5:0.565

What the agent learned: Malevolence fires as a rare per-take SPIKE (most takes ~0.05, ~1-in-8 spikes to 1-2.5). best-of-64 is what reliably catches it: the champion take spiked Malevolence to 1.45 AND stayed clean (blend 3.25, genu 1.89), reward 3.012 -- vs round-4's best-of-64 top of reward 2.465 / malice 1.25 / blend 0.94. So round 5 is BOTH more malevolent and much cleaner.

🐉 Dragon

Winning instruction: “A primordial, colossal dragon pronouncing a grand decree of judgement, voice an impossibly deep subterranean bass at the floor of the register, flat and unwavering, slow, grand and thunderous. Immense subharmonic chest resonance booming from a vast cavern of a chest, deep guttural throat rumble grinding beneath, seismic, dark and full, every word a dramatic proclamation. Utterly dominant and immovable, crushing ancient authority, seething with wrathful contempt and prideful triumphant scorn. No brightness, no high notes. (deep rumble) High quality recording.”

Spoken line: “You dare enter my lair, mortal? Your bones will join the others.”

① champion · reward 3.21 · char 0.72 · emo 0.88 · blend 5.2 · genu 0.8 · WER 0.00 · 7s

② runner-up · reward 3.18 · char 0.79 · emo 0.79 · blend 4.1 · genu 1.0 · WER 0.00 · 7s

③ third · reward 3.10 · char 0.79 · emo 0.79 · blend 4.1 · genu 1.0 · WER 0.00 · 7s

Loudest VoiceNet dims (champion): Fullness 5.7Throat Resonance 4.6Storytelling Style 4.6Chest Resonance 4.3
Top emotions: Anger 3.7Malevolence/Malice 2.9Contempt 2.5

This character’s fitness target: None

Character-fit across rounds: r1:0.569 → r3:0.724 → r4:– → r5:0.648

What the agent learned: Naming the resonance CAVITY concretely was the biggest lever: 'immense subharmonic chest resonance booming from a vast cavern of a chest, deep guttural throat rumble grinding beneath' (d_chest, gen2 winner 2.514) beat the round-3 champion's generic 'enormous chest resonance'. Deep chest/throat bass is best evoked by the cavity-as-a-place image, not by adjectives like 'deep/bass' alone.

👻 Evil Ghost

Winning instruction: “A hushed evil ghost whispering doom, breathy and hollow, all air and no chest, a cold ethereal whisper, clean and clear, sinister and menacing. Seething with quiet malice and contempt, a dreadful whispered threat, tense and controlled. Wicked, cruel and full of dread. No warmth, no fullness, no brightness. (soft hiss) High quality recording.”

Spoken line: “You should not have come here... this house feeds on the living.”

① champion · reward 3.93 · char 0.68 · emo 0.75 · blend 6.8 · genu 1.3 · WER 0.00 · 7s

② runner-up · reward 3.86 · char 0.61 · emo 0.76 · blend 6.6 · genu 1.4 · WER 0.00 · 12s

③ third · reward 3.28 · char 0.47 · emo 0.50 · blend 9.5 · genu 1.4 · WER 0.00 · 7s

Loudest VoiceNet dims (champion): Voice Age 6.0Fullness 5.6Storytelling Style 5.5Roughness 5.0
Top emotions: Malevolence/Malice 2.0Fear 1.8Contempt 1.5

This character’s fitness target: None

Character-fit across rounds: r1:– → r3:– → r4:0.592 → r5:0.676

What the agent learned: Pushed the whisper much harder (S_WHIS x2.5) but added explicit CLEANLINESS clauses ('clean and clear', 'every word clear', 'never breaking into noise', 'controlled') so the higher-weighted blend/genu are not sacrificed -- a hollow airy ghost-whisper that is still eerily intelligible.

🐭 Cartoon Mouse

Winning instruction: “A teeny cartoon mouse squeaking right at the very ceiling of the register, extremely high and tiny, thin and pinched, a bright glassy ringing head voice buzzing through the nose, tense and piercing. The pitch skitters and leaps giddily way up to the top and darts back down, wide and darting. Amazed, wide-eyed, astonished, delighted and eagerly curious. Weightless and baby-young, no chest, no fullness, no depth, meek, no authority. Piercing but clean and cute, every squeak crisp and clear. (astonished gasp) High quality recording.”

Spoken line: “Eee, wait, wait! Ooh, did you see it? Did you see how teeny-tiny it was?”

① champion · reward 3.40 · char 0.81 · emo 0.89 · blend 2.7 · genu 1.4 · WER 0.00 · 12s

② runner-up · reward 3.12 · char 0.82 · emo 0.73 · blend 5.2 · genu 1.1 · WER 0.12 · 8s

③ third · reward 3.04 · char 0.88 · emo 0.82 · blend 0.2 · genu 1.3 · WER 0.06 · 12s

Loudest VoiceNet dims (champion): Emphasis 5.1Dynamic Arc 5.0Dramatic Style 5.0Storytelling Style 4.6
Top emotions: Interest 3.2Astonishment/Surprise 2.7Elation 2.7

This character’s fitness target: mouse CFG: pos BRGT,R_HEAD,R_NASL,S_CART,TENS,RANG,REGS; neg AGEV,R_CHST,FULL,S_AUTH; vn_w RANG2.5/REGS2.0/BRGT1.8/R_HEAD1.5; emo Amusement/Elation/Interest/Astonishment; w_vn2.0 w_emo1.5 w_blend0.9 w_genu0.9; wer soft.

Character-fit across rounds: r1:0.752 → r3:0.757 → r4:0.869 → r5:0.805

What the agent learned: Squeaky/astonished interjections written INTO the text (Eee.../Ooh.../Wow!) lift char_emo (Astonishment/Amusement/Elation) AND S_CART noticeably vs a plain excited line — writing the affect into the spoken words does what the instruction cannot.

🧚 Fairy

Winning instruction: “A sweet little fairy brimming with warm loving affection and giddy joy, feather-light and airy, very bright and glassy, floating high in a sparkling register with a lilting sing-song pitch swooping sweetly up and down. Tender, adoring and radiant, bubbling with elated delight. Pure head resonance, no chest, gentle and unassuming, never commanding. (delighted giggle) High quality recording.”

Spoken line: “Oh, hello there, little one! What a wonderful day to make a new friend!”

① champion · reward 3.23 · char 0.72 · emo 0.89 · blend 3.9 · genu 1.0 · WER 0.00 · 7s

② runner-up · reward 3.12 · char 0.71 · emo 0.77 · blend 3.2 · genu 1.5 · WER 0.00 · 7s

③ third · reward 3.06 · char 0.69 · emo 0.64 · blend 4.7 · genu 1.8 · WER 0.00 · 5s

Loudest VoiceNet dims (champion): Storytelling Style 5.8Emphasis 4.8Dramatic Style 4.7Register 4.5
Top emotions: Affection 3.3Elation 2.7Contentment 2.3

This character’s fitness target: None

Character-fit across rounds: r1:0.464 → r3:0.711 → r4:– → r5:0.724

What the agent learned: Front-loaded the JOY/LOVE emotion ('a sweet little fairy brimming with warm loving affection and giddy joy ... tender, adoring and radiant, bubbling with elated delight') instead of burying affect at the end, while keeping the round-3 register + lilting-sing-song + head-resonance core.

Intense & High-Arousal

🗯️ Ranting Fury

Winning instruction: “A furious ranting tirade at the breaking point, haranguing and browbeating, voice shredding and cracking, about to snap, seething with rage and named loathing, spitting venom, screaming hatred and withering contempt in your face, domineering, refusing to yield an inch. Harsh, tense, violently volatile, maximum arousal, explosive pounding consonants, hammering relentless emphasis, the pitch lurching violently high to low, escalating and more vicious. Roaring but every word still lands. (enraged shout)(seething snarl) High quality recording.”

Spoken line: “Enough! I am sick to death of this! You pathetic, spineless fool, how dare you, how DARE you waste my time again and again!”

① champion · reward 5.07 · char 0.93 · emo 0.85 · blend 0.7 · genu 1.1 · WER 0.00 · 10s

② runner-up · reward 4.73 · char 0.71 · emo 0.93 · blend 1.3 · genu 1.3 · WER 0.00 · 12s

③ third · reward 4.65 · char 0.80 · emo 0.89 · blend 0.4 · genu 0.6 · WER 0.00 · 11s

Loudest VoiceNet dims (champion): Emphasis 5.6Stance 5.5Dramatic Style 5.5Volatility 5.0
Top emotions: Anger 5.1Impatience and Irritability 4.6Contempt 3.3

This character’s fitness target: ranting CFG: pos S_RANT,AROU,TENS,VOLT,ATCK,EMPH,S_AUTH,STNC,RANG; neg none; vn_w AROU2.5/S_RANT1.8/TENS1.5/VOLT1.5; emo Anger/Impatience/Contempt/Bitterness/Malevolence; w_vn3.0 w_emo2.5 (blend/genu default 0.5); wer soft.

Character-fit across rounds: r1:0.648 → r3:0.802 → r4:0.798 → r5:0.925

What the agent learned: Explicit 'ranting/raving/haranguing tirade' language lifted S_RANT (weighted 1.8) from ~1.2 (round-4 champion) to ~2.0-2.8 on the best takes — naming the DELIVERY MODE, not just the rage, feeds the rant-specific dim the round-4 prompt was starving.

😱 Pain Scream

Winning instruction: “Maximum raw screaming in blind terror and unbearable physical agony, throat tearing, voice shredded, guttural and harsh, grating rasp ripping raw, each scream cracking higher and more frantic, breaking into gasping sobs between screams. Panic-stricken, terrified and helpless, thrashing, drowning in pain. Extreme, maximum arousal, extreme tension, violently volatile and completely out of control. Raw agonized screaming, throat tearing apart. (agonized scream) (sobbing gasp) High quality recording.”

Spoken line: “Aaargh! No! No! Au— it hurts— aaah— nngh— get it off me!”

① champion · reward 4.13 · char 0.69 · emo 0.92 · blend 1.2 · genu 1.6 · WER 0.33 · 10s

② runner-up · reward 4.03 · char 0.69 · emo 0.92 · blend 1.2 · genu 1.6 · WER 0.33 · 10s

③ third · reward 3.96 · char 0.68 · emo 0.81 · blend 1.7 · genu 2.2 · WER 0.39 · 11s

Loudest VoiceNet dims (champion): Ranting/Angry Style 5.1Emphasis 5.0Dramatic Style 5.0Volatility 4.8
Top emotions: Distress 4.1Helplessness 3.3Pain 3.0

This character’s fitness target: None

Character-fit across rounds: r1:0.846 → r3:0.714 → r4:0.737 → r5:0.712

What the agent learned: A SECOND affect burst decisively paid off here (as the brief predicted): the paired '(agonized scream) (sobbing gasp)' double burst -- scream + emotional sob -- beat any single burst. It was the exact lever that broke the round-4 char vs char_emo tradeoff, letting the winner hit BOTH char 0.69 and char_emo 0.92 with AROU ~4.8 (round-4 champ topped out at char_emo 0.94 but only when char collapsed).

Intimate / ASMR

🌙 ASMR Man

Winning instruction: “A deep, soothing man whispering tenderly, soft and breathy, intimate close-mic, slow and gentle, a warm low chest resonance cushioning each word. Overflowing with tender affection, loving and reassuring, every worry melting away, wrapped in calm and drifting, deeply content, serene and utterly at peace, breathing out a soft sigh of relief. Utterly gentle and unassuming, meek, yielding, no authority whatsoever. Clear whispered words. (soft breath) High quality recording.”

Spoken line: “Just relax now, let it all go. You are safe here, close your eyes.”

① champion · reward 3.31 · char 0.62 · emo 0.88 · blend 6.9 · genu 1.1 · WER 0.00 · 8s

② runner-up · reward 3.08 · char 0.65 · emo 0.62 · blend 8.2 · genu 1.3 · WER 0.00 · 7s

③ third · reward 3.06 · char 0.64 · emo 0.78 · blend 3.8 · genu 1.4 · WER 0.00 · 12s

Loudest VoiceNet dims (champion): Warmth 4.2Voice Age 3.9Monologue Style 3.7Casual Style 3.4
Top emotions: Contentment 3.3Relief 2.6Affection 2.1

This character’s fitness target: None

Character-fit across rounds: r1:0.666 → r3:0.615 → r4:– → r5:0.625

What the agent learned: Added an explicit EMOTION-narrative layer to the spoken-affect description: 'every worry melting away, wrapped in calm and drifting, deeply content, serene and utterly at peace, breathing out a soft sigh of relief'. This drove the EmoNet Affection/Contentment/Relief heads hard, lifting best-of-64 char_emo from 0.669 (round 3) to 0.884 while keeping WER perfect.

🌙 ASMR Woman

Winning instruction: “A loving mother cradling her child to sleep, cheek to cheek, breathing love into every word. Extremely soft, breathy, intimate close-mic whisper, slow, hushed and quiet, a beautiful silken velvety-smooth tone, unmistakably and softly feminine, silvery light and delicate. Warm, tender, adoring and maternal, full of affection and serene contentment, a soft sigh of relief. Meek, gentle and yielding, never bossy or commanding. Whispered but every word clear. (soft breath) High quality recording.”

Spoken line: “There now, my love. Close your eyes. I have you, safe and warm.”

① champion · reward 2.98 · char 0.82 · emo 0.56 · blend 8.7 · genu 1.3 · WER 0.08 · 7s

② runner-up · reward 2.90 · char 0.77 · emo 0.53 · blend 5.6 · genu 1.3 · WER 0.00 · 9s

③ third · reward 2.88 · char 0.61 · emo 0.80 · blend 5.3 · genu 0.9 · WER 0.00 · 8s

Loudest VoiceNet dims (champion): Warmth 5.6Whisper-Talk Style 5.5Voice Age 5.2Monologue Style 5.0
Top emotions: Affection 4.1Contentment 2.1Relief 1.7

This character’s fitness target: None

Character-fit across rounds: r1:0.491 → r3:0.624 → r4:– → r5:0.824

What the agent learned: Replacing the onomatopoeic opener "Shhh" with a clean maternal phrase ("There now, my love..." / "Sleep now, sweet one...") lifted the WER gate from invwer~0.786 (a fixed 1-word ASR error on "Shhh") to 1.000, structurally raising the reward ceiling for the WER-gated archetype. This was the single biggest round-5 lever.

Grief

😢 Grieving Woman

Winning instruction: “A grieving young woman, unmistakably and softly feminine, her crying rising into a shaking wail, sobbing hard, shaking and cracking, thick with tears, wet and trembling, wailing between broken words. Heartbroken and inconsolable, drowning in sorrow, helpless and aching with loss. Raw and vulnerable, breaking apart. (sob) High quality recording.”

Spoken line: “No... no, please... don't leave me too... I can't— I can't lose anyone else...”

① champion · reward 4.41 · char 0.67 · emo 0.96 · blend 7.4 · genu 2.1 · WER 0.06 · 12s

② runner-up · reward 3.92 · char 0.68 · emo 0.72 · blend 5.2 · genu 2.3 · WER 0.00 · 12s

③ third · reward 3.81 · char 0.61 · emo 0.70 · blend 8.0 · genu 2.0 · WER 0.00 · 12s

Loudest VoiceNet dims (champion): Vulnerability 5.7Cognitive Load 4.1Disfluency 4.1Casual Style 3.8
Top emotions: Distress 4.8Sadness 4.0Helplessness 3.9

This character’s fitness target: None

Character-fit across rounds: r1:– → r3:– → r4:0.706 → r5:0.668

What the agent learned: Round-5 rewards Arousal, so the round-4 "crying softly" champion lost; naming a CLEAR feminine subject ("a grieving young woman, unmistakably and softly feminine") plus escalation dynamics ("her crying rising into a shaking wail") pushed both Arousal (AROU up to ~2.7-3.3 on top takes) AND Sadness (~4.0) while GEND stayed clearly female — devastating grief text "No... no, please... don't leave me too... I can't— I can't lose anyone else..." outscored every other line on Sadness (T2/T5 devastated it).

😔 Grieving Man

Winning instruction: “A man breaking down in tears, his voice cracking, keening and choking, gasping and hitching between words, hard sobs catching in his throat, wet and shaking, barely able to speak. Devastated and guilt-stricken, drowning in grief and longing, helpless and lost. A man's low, masculine voice, raw and vulnerable, sobbing uncontrollably. (anguished sob) High quality recording.”

Spoken line: “It's my fault... I-I should have been there... I should have saved her.”

① champion · reward 4.69 · char 0.73 · emo 0.99 · blend 6.3 · genu 2.3 · WER 0.00 · 12s

② runner-up · reward 3.92 · char 0.69 · emo 0.70 · blend 8.2 · genu 2.0 · WER 0.00 · 7s

③ third · reward 3.62 · char 0.69 · emo 0.70 · blend 8.2 · genu 2.0 · WER 0.00 · 7s

Loudest VoiceNet dims (champion): Vulnerability 5.6Disfluency 3.9Cognitive Load 3.8Volatility 3.7
Top emotions: Sadness 4.5Distress 4.2Disappointment 3.6

This character’s fitness target: None

Character-fit across rounds: r1:– → r3:– → r4:0.623 → r5:0.732

What the agent learned: Pushed from the round-4 'voice cracking, on the edge of sobbing, fighting tears' (restrained) to OVERT hard crying -- 'breaking down in tears, gasping and hitching between words, hard sobs catching in his throat, sobbing uncontrollably'. Reflecting the round-5 reward (Arousal now a rewarded pos dim, Sadness x3.0), this lifted the best-of-64 char_emo from 0.894 to 0.99 and reward from 4.07 to 4.69.

Anonymized companion for double-blind review. All voices are synthetic, generated by an open-weight text-to-speech model with no reference recordings; all scores are produced by the perceptual models described here. No author, institution, or repository identifiers are included by design.