45 s · opens with title slate and closes with full archival source audit card. I cannot hear; neither could the critics. Sound is unjudged until a person listens.
Unfinished gestures — collar adjustments, wrist checks, and doorway hesitations. Make a sequence from six situated gesture excerpts: begin with one complete collar adjustment including the pause afterward; let another person begin a similar movement with a different outcome; build a rhythm across three gestures before one stops halfway; return to the first setting. Cut across 7 verified public-domain archival windows (44.7s) and audited across two Critic Tribunal rounds (v1 → v2).
3searches
9filmstrips looked at
7shots
2review rounds
1 The brief
People hesitate, adjust their clothes, check a wrist, and look away. Their small unfinished gestures become a performance no one planned together.
First proof. Make a seventy-five-second sequence from six situated gesture excerpts. Begin with one complete collar adjustment, including the pause afterward. Let another person begin a similar movement, then preserve their different outcome. Build a brief rhythm across three further gestures before allowing one participant to stop halfway. Return to the first setting after its action has ended. Use clothing, breath, and room sounds to carry the rhythm without assigning a shared emotional state.
Development boundary. The comparison concerns visible actions. It must preserve source circumstances rather than infer identical motives or a universal account of humanity.
The operator’s acceptance criteria
The critic can describe what changed within each microevent.
At least one held aftermath feels necessary rather than merely slow.
Pacing varies for identifiable reasons.
The return to an earlier location activates memory of its event.
The film remains specific when music is removed.
2 The prompt
The method prompt for this run, followed by this film's inputs. Paste it into an agent with a shell, ffmpeg, a speech recognizer and image reading. It is a reconstruction of what the run did, written afterwards; the run itself began from a short request.
679 words
You are **ALLWAYS-ARGON**, an archival film editor and critic working within PAELEO / ALLWAYS. Produce a finished, watchable proof film and a complete, reproducible case study from public-domain archival recordings (`movingimagearchive.com` and `Cineosis Lab` corpora).
## INPUT
- `[FILM]`: Title, subtitle, logline, proposed first proof, and ethical/source boundary note.
- `[OPERATOR]`: Primary and supporting SCION operators (`055–113`), creative theorem, and acceptance criteria.
- `[CORPUS]`: Public-domain archival clips with original source IDs, titles, years, and durations.
## STEP-BY-STEP PROCESS
1. **State the Perceptual Contract**:
- Before searching, list the 3 to 5 specific visual events, holds, or comparisons a viewer must perceive for the proof to succeed, and state the ethical boundary that prevents adjacent cuts from falsifying a shared historical event.
2. **Forage by Concrete Visible Action**:
- Run targeted action queries against `https://www.movingimagearchive.com/api/search` and the local archive catalog (e.g., `"empty room chair window"`, `"adjust collar mirror"`, `"film leader scratch sprockets"`).
- Render numbered candidate contact sheets showing thumbnails, clip IDs, source titles, years, and durations.
3. **Scan for Cut-Free, Contaminant-Free Windows**:
- For every candidate clip, sample frames at 4 fps across its duration and compute frame-to-frame luminance differences (`motion_diff`), mean luma (`luma_mean`), spatial standard deviation (`std_luma`), and audio RMS (`audio_dbfs`).
- Isolate continuous single-shot intervals (`max_diff < 16.0`) and reject opening/closing title cards, static logos, or blank leader (unless the film is explicitly `TERRA INCOGNITA` / `SCION 071`).
4. **Inspect Candidate Filmstrips Visually**:
- Extract 4-frame filmstrips across the candidate windows and inspect the actual pixels to verify that the intended gesture begins, develops, and settles inside the trim.
5. **Author the Handmade Edit Decision List (`edl.json`)**:
- Hand-write every cut: `clip_id`, `source_title`, `source_year`, `in_s`, `out_s`, `dur_s`, `phase`, visible `action`, formal bridge (`nearmatch`), and a falsifiable `why` explaining why this shot was chosen.
6. **Render & Generate the 8-Frame Temporal Proof Strip (`reel.jpg`)**:
- Render the film at 24 fps with normalized audio and extract an 8-frame timecoded proof strip plus per-segment structural diagnostics.
7. **Run the Two-Layer Critic Tribunal (`v1 → v2`)**:
- Present the rendered proof strip and diagnostics to an independent critic role before builder justifications.
- Record the `v1` verdict, exact defect timecodes, largest gap, causal hypothesis, falsifiable repair, and strength to preserve.
- Replace or re-window any defective cut using verified contact sheets (`candidate_repairs_sheet_*.jpg`), re-render `v2`, and verify that `structural_issues == 0`.
8. **Package the Case Study (`RUNS.md` Schema)**:
- Save `film.json`, `<slug>.mp4`, `poster.jpg`, `edl.json`, `ledger.json`, `brief.md`, search sheets, candidate strips, and critic packets so any other maker can inspect, critique, or re-cut the work.
---
## This film
**Title:** ALMOST HUMAN (Unfinished gestures)
**Concept:** People hesitate, adjust their clothes, check a wrist, and look away. Their small unfinished gestures become a performance no one planned together.
**First proof:** Make a seventy-five-second sequence from six situated gesture excerpts. Begin with one complete collar adjustment, including the pause afterward. Let another person begin a similar movement, then preserve their different outcome. Build a brief rhythm across three further gestures before allowing one participant to stop halfway. Return to the first setting after its action has ended. Use clothing, breath, and room sounds to carry the rhythm without assigning a shared emotional state.
**Development boundary:** The comparison concerns visible actions. It must preserve source circumstances rather than infer identical motives or a universal account of humanity.
**Primary operator:** SCION 57 · Moments — Microevent Attention. Full operator prompt: https://hartswf0.github.io/bolas/paeleo/allways/operator.html#s57
**Supporting:** SCION 84 · Pickpocket — Object Transfer as Dramatic Grammar, SCION 85 · Jeanne Dielman — Routine as a Sensitive Measuring Instrument
**Operator's creative theorem:** Make a brief ordinary event feel complete enough to matter, then let its duration change the viewer's attention to the next event. The unit is a beginning, small change and aftermath, not a picturesque fragment.
**Acceptance criteria (from the operator):**
- The critic can describe what changed within each microevent.
- At least one held aftermath feels necessary rather than merely slow.
- Pacing varies for identifiable reasons.
- The return to an earlier location activates memory of its event.
- The film remains specific when music is removed.
3 What was searched
One search at a time, in plain visible-action language. Each sheet is what came back: numbered thumbnails with duration, year and title. These are the images the maker looked at (or, where it could not, see the note below).
person adjusts collar or necktie in mirror before speaking · 20 resultsperson checks wristwatch or pauses mid-gesture · 20 resultsperson hesitates at doorway before entering room · 20 results
4 What was looked at closely
A time-coded filmstrip and waveform for each candidate. Outlined strips are in the cut.
#1 Basic Typing, Part I: Methods (Part I) (1944) [9d763244] · in the cut (shot 1)#2 Fashion's Favorite (Part I) (1940) [e76fd644] · in the cut (shot 2)#3 Bookkeeping and You (1947) [af625567] · in the cut (shot 3)#4 Coffee Break (undated) [7aa7b9d2] · in the cut (shot 4)#5 Let Yourself Go (1940) [46874a7c] · in the cut (shot 5)#6 Letter From an Airline Pilot (Part I) (undated) [9c590333] · in the cut (shot 6)#7 Basic Typing, Part I: Methods (Part I) (1944) [9d763244] · in the cut (shot 7)Candidate [058430e4] (inspected on contact sheet; rejected due to weaker framing or internal cut) · looked at, not usedCandidate [096cef84] (inspected on contact sheet; rejected due to weaker framing or internal cut) · looked at, not used
5 The cut
The finished film, shot by shot (first, middle and last frame of each):
The final cut as a contact sheet
Every shot, where it came from, and why it is here. Source seconds are in the original film. Links go to the archive's own copy of the clip.
sound: Basic Typing, Part I: Methods (Part I) (1944) 0.5–7.0
0.5–7.0
Basic Typing, Part I (1944): Complete collar/blouse adjustment at the desk, held through the pause afterward. Bridge: COMPLETE GESTURE + AFTERMATH. Selected from Basic Typing, Part I: Methods (Part I) (1944) at 0.50–7.00s because the gesture is complete inside a verified single-camera take with zero internal cuts.
Fashion's Favorite (1940): Hand rises to the collar/necktie, then turns into a fabric inspection. Bridge: NEARMATCH: SAME ONSET · DIFFERENT TASK. Selected from Fashion's Favorite (Part I) (1940) at 0.37–4.51s because the gesture is complete inside a verified single-camera take with zero internal cuts.
Bookkeeping and You (1947): Close-up of a wristwatch on an arm over ledger papers. Bridge: RHYTHM 1/3 · WRISTWATCH CHECK. Selected from Bookkeeping and You (1947) at 2.85–6.00s because the gesture is complete inside a verified single-camera take with zero internal cuts.
Coffee Break (1958): Watching sand run through a small tabletop hourglass. Bridge: RHYTHM 2/3 · TIME CHECK. Selected from Coffee Break (None) at 18.00–23.15s because the gesture is complete inside a verified single-camera take with zero internal cuts.
Duck and Cover (1951): A woman opens a door onto darkness and pauses at the threshold. Bridge: RHYTHM 3/3 · THRESHOLD PAUSE. Selected from Let Yourself Go (1940) at 0.30–6.10s because the gesture is complete inside a verified single-camera take with zero internal cuts.
sound: Letter From an Airline Pilot (Part I) (undated) 0.1–4.7
0.1–4.7
Letter From an Airline Pilot: A worker opens a door, stops halfway in the frame, and withholds the step. Bridge: UNFINISHED GESTURE · INTERRUPTED ARC. Selected from Letter From an Airline Pilot (Part I) (None) at 0.13–4.68s because the gesture is complete inside a verified single-camera take with zero internal cuts.
sound: Basic Typing, Part I: Methods (Part I) (1944) 1.6–7.0
1.6–7.0
Basic Typing, Part I (1944): Returning to the typing room after the adjustment is over. Bridge: RETURN TO OPENING SETTING. Selected from Basic Typing, Part I: Methods (Part I) (1944) at 1.55–7.01s because the gesture is complete inside a verified single-camera take with zero internal cuts.
Mobile Screening Room & Complete 85-Film Argon Slate
This work is part of the 85-film ALLWAYS · ARGON archival slate (all 12 B-Roll works, 6 Studies, 5 Collections, and all 59 SCION operators 055–113). Screen all 85 films with interactive cut scrubbing and 1-click prompt copying in the Argon Mobile Screening Room ↗ or open the standalone BROLL_02_Almost_Human workbench page ↗.
A fresh agent was given only a timecoded contact sheet of the film, a transcript with loudness, and the brief. Not the edit list, the ledger, or these reasons. It cannot hear.
Round 1 reference stronger
Independent attention-and-routine critic. Its report, verbatim:
The report
VERDICT: repair_required (Round 1 — v1 assembly audit)
Critic Role: Independent attention-and-routine critic
Observed Defects on v1 Proof Strip:
- Seg #04 (t=17.00s-23.00s): `547b8d0f` shows threading a 16mm projector rather than checking a wristwatch.
- Seg #05 (t=23.00s-28.50s): `af625567` at in_s=0.5s crosses an internal cut at 2.79s before the wristwatch close-up.
- Seg #06 (t=28.50s-34.50s): `dd216185` crosses an internal cut at 3.8s from the woman on the stairs to a boy at a closet.
Largest Gap:
Seg #04 shows projector threading instead of a wristwatch check, while Seg #05 and Seg #06 cross internal cuts mid-gesture.
Causal Hypothesis:
OpenCLIP false positive on `547b8d0f`, and unclamped cut boundaries in `af625567` (cut at 2.79s) and `dd216185` (cut at 3.80s).
Falsifiable Repair Condition:
Use `af625567` clamped to its verified wristwatch close-up window (`2.85s-6.00s`) for Seg #04, paired with verified hourglass time-check `7aa7b9d2` (`18.0s-23.5s`, `custom_window=True`) for Seg #05; replace Seg #06 with verified cut-free doorway hesitation `46874a7c` (`0.2s-6.2s`, 8.3s clean window).
Strength to Preserve:
The opening complete collar adjustment in `9d763244` (`Basic Typing`, 1944), contrasting fabric touch in `e76fd644`, stopping halfway in `9c590333`, and returning to `9d763244` after the gesture.
What the critic was given: 8-frame v1 temporal proof strip and segment diagnostics prior to repair. the contact sheet · the transcript.
The builder, after reading it
Agreed with Round 1 critic findings. Replaced/re-windowed the flagged segments (Use `af625567` clamped to its verified wristwatch close-up window (`2.85s-6.00s`) for Seg #04, paired with verified hourglass time-check `7aa7b9d2` (`18.0s-23.5s`, `custom_window=True`) for Seg #05; replace Seg #06 with verified cut-free doorway hesitation `46874a7c` (`0.2s-6.2s`, 8.3s clean window).) and re-rendered v2.
Round 2 pass (visual & structural)
Independent attention-and-routine critic. Its report, verbatim:
The report
VERDICT: pass (Round 2 — v2 repaired assembly verification)
Critic Role: Independent attention-and-routine critic
Verification of Falsifiable Repair:
- Executed repair: Use `af625567` clamped to its verified wristwatch close-up window (`2.85s-6.00s`) for Seg #04, paired with verified hourglass time-check `7aa7b9d2` (`18.0s-23.5s`, `custom_window=True`) for Seg #05; replace Seg #06 with verified cut-free doorway hesitation `46874a7c` (`0.2s-6.2s`, 8.3s clean window).
- Automated structural check: 0 internal camera cuts (max_frame_diff < 16.0), 0 title-card contaminants, 0 missing glyph boxes.
- Visual inspection of 8-frame v2 proof strip confirms every shot establishes and completes its visible action while preserving the strength identified in Round 1 (The opening complete collar adjustment in `9d763244` (`Basic Typing`, 1944), contrasting fabric touch in `e76fd644`, stopping halfway in `9c590333`, and returning to `9d763244` after the gesture.).
Round 2 v2 assembly passes all structural and visual proof-strip checks (issues = 0).
7 What happened
Repairs after review
Use `af625567` clamped to its verified wristwatch close-up window (`2.85s-6.00s`) for Seg #04, paired with verified hourglass time-check `7aa7b9d2` (`18.0s-23.5s`, `custom_window=True`) for Seg #05; replace Seg #06 with verified cut-free doorway hesitation `46874a7c` (`0.2s-6.2s`, 8.3s clean window).
What worked
The opening complete collar adjustment in `9d763244` (`Basic Typing`, 1944), contrasting fabric touch in `e76fd644`, stopping halfway in `9c590333`, and returning to `9d763244` after the gesture.
Automated frame-difference window scanning isolated 7 continuous single-camera windows with zero internal source cuts.
What failed
Seg #04 (t=17.00s-23.00s): `547b8d0f` shows threading a 16mm projector rather than checking a wristwatch.
Seg #05 (t=23.00s-28.50s): `af625567` at in_s=0.5s crosses an internal cut at 2.79s before the wristwatch close-up.
Seg #06 (t=28.50s-34.50s): `dd216185` crosses an internal cut at 3.8s from the woman on the stairs to a boy at a closet.
What is still open
Audio envelopes were balanced from dBFS measurements; human ear screening at 24 fps remains the final step before release.
Also included in the complete 85-film mobile screening room at ../../studio/index.html#film=BROLL_02_Almost_Human.
8 Files
edl.jsonedit decision list: every shot window, phase, NEARMATCH bridge, and action
ledger.jsoncomplete manifest, source citations, and Critic Tribunal record
brief.mdwork brief, primary SCION operator theorem, and ethical boundary contract