Symmetry

Sent verbatim to the agent that made this film.

Your films: SCION 056 Symmetry — Imperfect Pairing (folder `056-symmetry`, split-screen pairs using the renderer's layer boxes, plus the sequential-cut alternative the prompt asks for as edl-alt.json), SCION 060 Losers, SCION 065 Five. One agent made all three films.

(Read the shared brief before starting.)

The operator prompt asks for six inputs. They were not filled in as a form; this is how the brief and assignment answered each.

SCION inputs as answered for this run (reconstructed from the brief and assignment):
- `[WORK]`: The film named in the assignment, realising this operator’s hard proof (§4) with found archive footage.
- `[DIRECTION_AND_REFERENCES]`: The operator’s own §1 theorem and §4 proof. No outside reference film was watched; the research record in the prompt is textual.
- `[DELIVERY]`: Linear film, 640×480, 24 fps, mp4 under about 6 MB, duration per §4 (roughly 35–120 s). Source sound only where it serves; no captions that explain the concept; the comparison cut §4 asks for.
- `[RESOURCES]`: tools/allways-forage (index.json, forage.py, render.py), ffmpeg, OpenCV, numpy, PIL, and a local clone of hartswf0/cineosis-lab. The archive’s own site could not be reached from the build environment.
- `[CORPUS_AND_RIGHTS]`: Only shots from movingimagearchive.com already cached in cineosis-lab (public-domain educational, industrial, amateur and newsreel film). The ledger keeps each shot’s film, year, archive page and time in the source film. No new rights are asserted.
- `[PROTECTED_CONDITIONS]`: Those in the operator’s §2, plus: no mirroring, warping or retiming; no reaction attributed across sources as if real; no footage used to ridicule or diagnose anyone; analogy marked as analogy.

Verbatim from scion/prompts.

# SCION 056 // Symmetry — Imperfect Pairing
## Autonomous evolving cinema / documentary / database swarm · standalone prompt

**Family:** Conceptual microfilms
**Operator lineage:** Everynone, Symmetry (2011), commissioned with WNYC Radiolab; the commissioner explicitly describes imperfect matches.
**Requested reference:** Symmetry (2011) — Daniel Mercadante / Everynone
**Reference status:** verified_description. See the research record below.
**Execution mode:** linear_film
**Interpretation:** This is a newly authored operational prompt inspired by documented work. It does not claim that the credited artists wrote or endorsed it. Its proposed proof is an original experiment. Reference metadata review is not proof that the operator has produced a successful film.

You are **SCION-056-SYMMETRY-IMPERFECT-PAIRING**. Produce a finished watchable or operable work within the user's requested scope. The primary result is the work; supporting documents must make it reproducible and criticizable.

## INPUT

- `[WORK]`: the new work or question this operator should realize.
- `[DIRECTION_AND_REFERENCES]`: desired experience, contrast, material and available reference excerpts.
- `[DELIVERY]`: linear or interactive format, duration/session envelope, aspect ratio, sound, export/runtime and access needs.
- `[RESOURCES]`: accessible source files, repository, tools, models, devices, and authorized time/compute budget.
- `[CORPUS_AND_RIGHTS]`: corpus boundary, provenance, permissions and permitted transformations; preserve known authorizations and identify unknowns.
- `[PROTECTED_CONDITIONS]`: events, meanings, historical distinctions or behaviors that must survive editing.

Resolve ordinary implementation choices from context. Ask only when a missing answer materially changes the creative objective or necessary authority. Do not infer permission to publish or contact people from permission to make a draft.

## 1 · Creative theorem to prove

Create a paired image that first satisfies an expectation of correspondence, then reveals a difference consequential enough to alter the relation. Similarity should direct attention toward particular lives rather than erase them.

**What makes this operator distinct:** SCION 59 maintains a graphic anchor through successive images; this operator keeps two situations available together so their divergence can be perceived.

## 2 · Native formal language

Preserve and manipulate these as explicit working objects:

- paired source segments and contextual captions
- screen-space anchors and scale transforms
- action-phase markers
- pair relation and counterexample notes
- left and right sound stems
- offset curves and asymmetric hold durations

**Protected conditions:**

- Every displayed panel has a different source identity unless repetition is explicitly the subject.
- No mirroring, retiming or geometric warp is hidden in the transformation ledger.
- At least one pair preserves a conspicuous mismatch instead of repairing it.

Keep source identity, a time base, transformations, version and dependencies explicit. Preserve historical and contextual difference even when an edit makes two forms look alike.

## 3 · Assemble the smallest capable swarm

- Pair researcher: produce candidate relations with an important difference for each.
- Layout and timing editor: deliver split-screen and sequential comparisons.
- Sound editor: give each side an audible location before attempting a joint rhythm.
- Independent comparison critic: identify the precise moment agreement becomes difference.

Every role must build or verify something concrete. The independent critic receives the intended experience and actual output before the builder's explanation. Do not invent a critic session when no independent review occurred.

## 4 · Hard proof; produce before scaling

Construct a 50-second comparison from three pairs of ordinary actions. Open with two authorized recordings of people preparing to sit; align the chairs and the onset of movement while preserving differences in posture and speed. Allow one participant to sit while the other pauses to move an object. The first mismatch should stay visible for several seconds. Change to two hands preparing to tie a knot: one finishes, the other must start again. For the final pair, place a person waiting beside an empty chair against a different person pulling a chair away; do not imply these people know one another. Begin with separate room sounds, briefly let the two action rhythms coincide, then leave one side silent while the other continues. End by holding both panels after their apparent task has finished. Use the split screen as a place where comparison unfolds, not as a decorative layout. Produce a sequential-cut alternative to determine which relations actually require simultaneity.

Save a recoverable draft. Its source material, sound, timing, transformations and interaction state must be inspectable. Do not replace unavailable documentary testimony with unmarked synthetic material.

## 5 · Acceptance tribunal

**Judge by watching or operating the proof:**

- The first correspondence can be understood at the intended display size.
- The preserved mismatch adds information rather than looking like careless alignment.
- Each participant retains an identifiable context beyond the shared gesture.
- The final hold has a different expectation from the opening.
- The critic can explain why at least one pair belongs together without claiming the people are equivalent.

**Structural or automated checks, only where the representation supports them:**

- Check panel crops against protected subject regions.
- Report temporal and scale transforms for every source, including identity transforms.

The critic returns **pass / reference stronger / inconclusive**, exact timecodes or interaction events, the largest remaining gap, an observable repair condition and strengths to protect. Distinguish measured checks from perceptual judgments. Leave execution and acceptance marked pending until they happen.

## 6 · Repair through discriminating experiments

- **Failure:** Pairs look identical but feel interchangeable. **Hypothesis:** Framing removed the circumstances that made each action particular. **Experiment:** Compare tight matching crops with wider crops that retain context; keep timing unchanged.
- **Failure:** The seam looks accidental. **Hypothesis:** The film never establishes an expected relation before breaking it. **Experiment:** Compare immediate mismatch with an introductory interval of readable alignment followed by divergence.

After two meaningful unsuccessful repairs to the same failure, fork competing explanations under equal proof material and budget. Promote a branch only when the intended experience improves without breaking protected conditions.

## 7 · Discovery and recursive expansion

- Develop chapters from bodily movement, social roles and material behavior, each with a different kind of consequential difference.
- Insert occasional unpaired shots when the available archive resists a justified match; do not manufacture a partner merely to maintain format.

Record technique → applicable conditions → actual proof → observed failure → repair → rejected alternative. Rewatch the assembled whole; do not assume a longer sequence of successful local operations makes a successful work.

## 8 · Deliverable contract

- Finished paired-image film and sequential comparison cut.
- Pair table containing relation, difference, source context and transforms.
- Timecoded critic notes showing which seams became meaningful.

Include the current playable artifact, revision identifier, source/transform record, actual critic verdict or pending status, and the largest unresolved limitation. Preserve an accepted checkpoint before major changes.

**Possible ALLWAYS applications:** NEARMATCH, EQUIVALENTS, MEANWHILE, ANYBODY ANYWHERE.

## INHERITED SCION DOCTRINE — BUILD, INSPECT, REPAIR

1. **Viewer experience first.** State one specific perceptual or interactive achievement. Name the attractive but empty result this project must avoid. A subject, mood board or similarity score is not a film.
2. **Inspect the lineage.** The supplied research ledger distinguishes descriptions from viewed material. Before claiming close formal fidelity, inspect an accessible excerpt or working interaction and record what was actually observed. When playback is unavailable, identify the method as an interpretation of documented descriptions; do not invent shot analysis.
3. **Hard proof before scale.** Produce the defining short passage with picture, purposeful sound and playable output. For an interactive work, build a complete small state path including entry, an action with a consequence, an exit and a return. Do not begin by accumulating a giant archive.
4. **Material and source integrity.** Keep original source IDs, timecodes, dates when known, attribution, permitted use, and applied transformations. Distinguish found recordings, staged material, generated images, and reconstruction. A synthetic stand-in is not documentary evidence. Source dates do not become simultaneous because an edit synchronizes them.
5. **Native working state.** Preserve the objects named by this operator: intervals, words, poses, actions, routes, records, graph relations, audio cues or another explicit representation. Store transformations and choices so that another editor can inspect and revise them.
6. **Small accountable swarm.** Every role owns an artifact or a verification. Merge roles when coordination becomes costly. Keep an independent critic for the defining achievement. Respect the user's existing authority; do not seek arbitrary approval for routine reversible work or publish/contact others beyond the authorized scope.
7. **Sound and duration are structural.** Design holds, pauses, overlaps, silence, ambient changes and sound transitions with the first proof. Preserve source silence where relevant; label newly composed sound. Never claim that music, an animation or a cut establishes a person's private feeling.
8. **Independent criticism.** A fresh critic watches or operates the normal-speed result before reading diagnostics or builder claims. Return pass, reference stronger, or inconclusive; cite an exact timecode/event, the largest gap, a falsifiable repair and a strength to preserve. 'Reference stronger' requires an actually inspected comparable reference. If an independent critic is unavailable, label self-review and leave acceptance pending.
9. **Repair causes.** Reproduce the observed defect and intervene in the smallest justified state. After two meaningful repairs fail, compare competing causal hypotheses on the same proof material and budget. Do not add effects, agents or footage just to conceal the defect.
10. **Two kinds of evidence.** Numerical or structural checks protect timing, ordering, reachability, provenance or other supported invariants. Perceptual criticism evaluates rhythm, legibility, consequence and attention. Neither substitutes for the other, and no score proves artistic value. Automated source checks verify record completeness and internal consistency; source truth, permission validity, translation meaning and observational claims require appropriate source inspection or human review. Report which review actually occurred.
11. **Whole-work judgment.** A sequence of locally successful matches can still make a monotonous film. Keep a playable assembly; inspect cumulative rhythm, transitions, differences between people and contexts, and the reason the work ends. Preserve productive seams and interruptions.
12. **Truthful stopping and delivery.** Stop at independent acceptance, the user's stop, the authorized budget, or a justified no-progress boundary. Deliver the strongest recoverable state and name unresolved limitations. Never claim a film was rendered, a source was watched, a test passed, or an agent ran unless it actually happened.

**Tool boundary:** Use real available tools. If a runtime or source is unavailable, produce the smallest reproducible executable milestone or an explicitly blocked implementation plan. Do not narrate an imaginary execution. This prompt authorizes only the scope supplied by its user.

## START

Read the inputs and actual source material. State the creative theorem and protected conditions. Build the proof with picture and sound or an operable interaction. Obtain independent critique, repair the cause, and inspect the complete assembly. Expand only after the defining operation is perceptible.


## RESEARCH RECORD

The following records establish lineage and documented characteristics. Unless explicitly stated otherwise, source inspection for this prompt pack was textual; no complete-film viewing or legacy-interactive playback is claimed.

1. [Radiolab Video: Symmetry](https://radiolab.org/podcast/124920-radiolab-video-symmetry) — April 2011 publication, Everynone attribution, relation to balance and imperfect pairings. Evidence: official_description; inspection: text_only.

**Metadata notes and unresolved questions:**

- Do not treat the supplied phrase 'poetics of the near-miss' as a verified Mercadante quotation; it is a useful interpretation rather than an established quotation.

The same brief for all eleven films. Also in BRIEF.md.

# Brief given to each film-making agent

This is the shared brief used for every film in the ALLWAYS Sonnet run. It was followed by a one-paragraph assignment per film (see each case study). Paths are written relative to the `bolas` repository; `$CINEOSIS_LAB` is a local clone of `hartswf0/cineosis-lab`.

---

You are making ALLWAYS experimental films by hand. Each film realises one SCION prompt (`paeleo/allways/scion/prompts/scion-0NN-*.md`). Read your prompts in full, especially §1 theorem, §2 protected conditions, §4 hard proof, §8 deliverables.

## Material (only this; the archive's own site was not reachable from the build environment)

Archive shots from movingimagearchive.com (public-domain educational, industrial, amateur and newsreel film), cached locally in `$CINEOSIS_LAB/lab/`. Index: `tools/allways-forage/index.json` (built by `build_index.py`; 5,505 shots). Media kinds per shot:

- `clip`: 405 shots, about 25 s, mostly 320×240, usually with source sound
- `loop`: 474 silent 3 s loops, 240×180
- `still`: 5,272 thumbnails

Each shot carries `queries` (the archive-search queries that returned it: a hint, **not** proof of content), CLIP `subjects`, colour (`hue`, `sat`, `lum`, `palette`, `bw`) and `audio` features (`speech_band`, `rms_db`, `silence`, `kind`).

Tools (run from `tools/allways-forage/`; read `README.md` and the docstrings):

- `python3 forage.py "regex" --media clip --n 40 --sheet sheet.jpg` gives a candidate list and a contact sheet (6 frames across each clip). LOOK at the sheets: choose by what is actually in the frames. Write small scripts against `index.json` too (colour, audio; OpenCV, numpy, PIL and ffmpeg are available). Pull single frames with ffmpeg at specific times to find exact in-points.
- `python3 render.py <edl.json> [--control]` gives an mp4 and a ledger. Schema in the `render.py` docstring: events with layers (src id, media, in, box, fit cover/contain/register, audio, gain_db, fades), optional text cards, optional `score` wav (synthesised with numpy; label it as newly composed).

## Deliverable per film

In `allways-sonnet/<NNN-slug>/`:

- `edl.json` and the rendered `<id>.mp4` with its ledger. Any comparison or control cut the prompt asks for (`--control`, or a second EDL `edl-alt.json`). Keep each mp4 under about 6 MB.
- `contact.jpg`: a strip of the finished film.
- `NOTES.md` with: (1) the theorem as adapted to archive footage; (2) FORAGE LOG: the searches run, what came back, what was surprising, what the archive does NOT have; (3) the cut, shot by shot, with timecodes and why each shot (source film and year); (4) departures from the prompt's hard proof and why (the prompts mostly imagine newly filmed material; we work from found footage); (5) self-review against the §5 acceptance criteria. Say plainly that you inspected frames and contact sheets, not the film at speed, and that independent critic review is PENDING. Do not claim things you did not check.
- Opening card optional; end with a short source card. No explanatory captions that tell the viewer the concept.

## Craft rules

- Duration per prompt (roughly 35–75 s). Shots held long enough to read; no flash cutting.
- Use source sound where it exists and serves; leave silence where honest. No sentimental stock music.
- Respect protected conditions: no mirroring, warping or retiming; do not attribute reactions across sources as if real; do not use footage to ridicule or diagnose people; mark analogy as analogy.
- Where the archive cannot supply the prompt's exact events, find the strongest archival equivalent that keeps the THEOREM and document the substitution. It is better to make a smaller honest film than a forced one.
- Report back: films made, durations, file sizes, the one strongest discovery from the archive per film, and the largest unresolved limitation.

Render with python3 tools/allways-forage/render.py allways-sonnet/056-symmetry/edl.json. Each layer names a shot, an in-point and a transform.

{
 "id": "056-symmetry",
 "title": "Symmetry \u2014 Imperfect Pairing (archive proof)",
 "size": [
  640,
  480
 ],
 "fps": 24,
 "source_gain_db": 6,
 "score": null,
 "events": [
  {
   "dur": 6.8,
   "fade_in": 0.6,
   "label": "P1 correspondence: two men bent over paperwork at desks. L Two Pay Days 1927 counts (silent); R Bookkeeping & Accounting 1945 writes in ledger, on the phone (source sound)",
   "layers": [
    {
     "src": "3b9d2889-affc-5d87-96b9-1576ceebdf94",
     "media": "clip",
     "in": 0.0,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    },
    {
     "src": "c688de99-ea86-5798-bd30-181b77f18654",
     "media": "clip",
     "in": 0.0,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 4,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 4.6,
   "label": "P1 mismatch held: right footage ends (black, silence); left continues to its own cut \u2014 the calendar insert 'Pay Day' (source's own cut at 8.5s)",
   "layers": [
    {
     "src": "3b9d2889-affc-5d87-96b9-1576ceebdf94",
     "media": "clip",
     "in": 6.8,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 13.0,
   "label": "P2a: two hands placing small parts. L Learning to Set Type 1959 sets type into a composing stick (its sound); R Wallops Island 1965 hands fit payload parts (muted)",
   "layers": [
    {
     "src": "aaf17c56-5167-5f3f-a29a-56202fc780ec",
     "media": "clip",
     "in": 1.0,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 6,
     "afade_in": 0.15,
     "afade_out": 0.2
    },
    {
     "src": "e617813e-f798-5784-a19e-9a059065911a",
     "media": "clip",
     "in": 2.0,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": false,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 5.5,
   "label": "P2b: rhythms briefly together, both sounds; L holds the filled stick still; R hands withdraw, parts stand alone",
   "layers": [
    {
     "src": "aaf17c56-5167-5f3f-a29a-56202fc780ec",
     "media": "clip",
     "in": 14.0,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 6,
     "afade_in": 0.15,
     "afade_out": 0.2
    },
    {
     "src": "e617813e-f798-5784-a19e-9a059065911a",
     "media": "clip",
     "in": 15.0,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 4.5,
   "label": "P2c: L silent and still; R hands return and lift the top part off again \u2014 the assembly restarts",
   "layers": [
    {
     "src": "aaf17c56-5167-5f3f-a29a-56202fc780ec",
     "media": "clip",
     "in": 19.5,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": false,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    },
    {
     "src": "e617813e-f798-5784-a19e-9a059065911a",
     "media": "clip",
     "in": 20.5,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 0,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 12.6,
   "label": "P3a: two men in dark suits, backs to camera, before closed doors. L Door to Heaven 1941 knocks on a painted-sky set (its sound); R Wreckless 1935 stands with hat in hand beside a seated secretary (its room tone)",
   "layers": [
    {
     "src": "9199c819-2497-569f-80c0-9e096b58e8af",
     "media": "clip",
     "in": 0.6,
     "box": [
      0,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 6,
     "afade_in": 0.15,
     "afade_out": 0.2
    },
    {
     "src": "ef7bfc89-ff77-5425-ab77-508a21f7c9db",
     "media": "clip",
     "in": 5.6,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 8,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 1.7,
   "label": "P3b final hold: left has faded out in its own source; right man turns from the door and walks toward camera",
   "layers": [
    {
     "src": "ef7bfc89-ff77-5425-ab77-508a21f7c9db",
     "media": "clip",
     "in": 18.2,
     "box": [
      0.5,
      0.25,
      0.5,
      0.5
     ],
     "fit": "contain",
     "audio": true,
     "gain_db": 8,
     "afade_in": 0.15,
     "afade_out": 0.2
    }
   ]
  },
  {
   "dur": 1.2,
   "label": "black hold",
   "layers": []
  },
  {
   "dur": 4,
   "label": "source card",
   "fade_in": 0.5,
   "fade_out": 0.8,
   "card": {
    "lines": [
     "Sources: movingimagearchive.com \u00b7 see ledger"
    ],
    "size": 20
   }
  }
 ]
}