Phenomainonresearch
Field manual · /guide

The Analyze Lab & the Workbench.

Everything the research desk gives you — from a single drag-and-drop forensic analysis to a persistent case file submitted for the permanent archive. This guide walks every panel, every control, and what the numbers actually mean.

Part 1 · /analyze

The Analyze Lab

Upload a photo or video of an aerial phenomenon and get a full forensic report: a dozen independent pipelines plus a frontier multimodal AI review, in one pass. One free analysis for everyone; unlimited with Research ($5/mo).

Uploading

1
Drop your files — nothing runs yet. Drag photos or videos onto the upload card, or hit Choose files. Up to 500 MB each. The media is staged, not sent: a review card shows what you picked, and nothing uploads until you hit Analyze — so there is always a moment to attach phone data or toggle Forensics first. Select several files from the same incident and the first is analyzed while the rest ride along as attachments for the case if you later file it.
2
Attach phone data (optional, powerful). Hit Attach phone data and add what the device itself recorded — one file, several, or a zip: a Google Takeout export, an iPhone “export unmodified originals” folder (clip + .AAE), a GPX from a GPS-logger app, a DJI flight-log SRT, a CSV/JSON sensor log, XMP sidecars. Everything inside is scanned: the track is checked against the media's own GPS and time (and auto-fills the capture place & time for the sky, air-traffic and weather pipelines); library records are checked against the file's capture time, location and device; a bundled copy of the clip is byte-compared to your upload. Attaching phone data switches Forensics on, so you always get the combined authenticity report. The two are different things: phone data is evidence you provide (what the device recorded); Forensics is the analysis that reads it and the file's structure. Forgot to attach it? A finished report offers Attach phone data & re-run — no re-upload of the media needed.
3
Watch the bar. One progress bar covers the whole journey: the upload fills the first stretch, then the analysis pipelines fill the rest stage-by-stage. A 30-second video takes 30–90 s of compute; big files queue politely. No file handy? Try a sample loads a released U.S. Navy flyby clip with its full report.
Reading the results

The report, panel by panel

The report leads with what we think it is — the AI reading, the detections and the motion timeline, with the Evidence Chat right there to interrogate them — then the tools, then two grouped sections: Environmental Analysis (the sky, air traffic, weather and scene around the capture) and Forensics (is the file what it claims to be), before filing.

Multimodal AI Analysis
included every run

A frontier multimodal model reviews one frame alongside our pipelines and gives a candidate-by-candidate reading with likelihoods. Advisory — it never changes the pipeline verdicts.

Objects detected · Motion events
computer vision

YOLO detections across sampled frames, and a motion-event timeline showing exactly when something moved — those events become one-tap starting points for the object tracker.

Blinking-light signature
video · hard numbers

The brightest flashing light in frame, measured frame-by-frame: flash period, on-duration, and timing steadiness. Aviation and tower obstruction lights flash at regulated rates (red tower beacons: 20–40/min), so a steady measured period is a strong mundane hint — reported as consistency with a light class, never an identification.

Evidence Chat
interrogate the case

Ask questions about this analysis in plain language — the assistant holds the full report as context, and you can push any Viewing-Lab frame into the conversation. The transcript rides along if you file the sighting.

Aircraft classification
custom-trained · 83 classes

A classifier trained on our own aircraft datasets names the closest type — or returns Unknown, the headline outcome, with the rejection evidence and the strongest counter-evidence from the other pipelines pulled in beside it. Think you know what it is? The “help identify” form feeds future classifier versions.

Environmental Analysis
grouped section

Everything demonstrably around the capture, in one place: Skyline & Celestial Layout, air traffic, weather history, mundane matches, scene context, optics, and clouds.

· Skyline & Celestial Layout
astronomy

From the capture place & time: planets, bright stars, the Moon, satellite passes, meteor showers, aurora conditions — with altitude/azimuth you can cite. If the media lacks GPS or a timestamp, one shared Resolve place & time form re-runs the whole report with your answers.

· Air traffic
live ADS-B

Aircraft near the capture point with bearing, distance, altitude, speed — the fastest mundane explanation there is, or a meaningful absence.

· Weather · history & clouds
context

Archived conditions at the capture hour (cloud cover, visibility, precipitation) plus a cloud-genus classifier on outdoor shots — lenticular clouds explain a lot of saucers.

· Mundane matches · Scene · Optics
reality checks

A dedicated pass for birds, kites, balloons, drones; indoor/outdoor + place type (an indoor “sky” is a red flag, as is a TV or phone screen in frame); and a lens-flare / bokeh geometry check for artifacts that mimic craft.

Forensics
grouped section · before filing

Is the file what it claims to be. Provenance forensics reads the container structure, capture keys, encoder fingerprints and timeline against what an iPhone or Android camera actually writes versus what CapCut, ffmpeg and NLEs write — verdict: camera-original / exported / stitched with every piece of evidence, one combined authenticity score, and the phone's own data (Takeout JSON, .AAE, XMP, GPS logs) cross-checked against the file. File-only: consistency with a device family, not proof of one specific phone.

· Authenticity
videos · 0–100 score

The frame & audio pass folded into Forensics (shown alone when Forensics is off): metadata & editing-software tags, duplicate-frame runs, abrupt scene cuts, audio splice jumps — heuristic provenance, not deepfake detection.

· Device telemetry
when attached

The parsed track (points, duration, distance, speed, altitude), the device's interpolated position at the capture moment, and a green/amber verdict on whether the track agrees with the media's own GPS. Disagreement is a finding.

Opt-in · photos & videos

Forensics — raw capture, export, or stitched?

In plain terms: every phone camera leaves a very specific set of fingerprints inside the file it records — not in the picture, but in how the file is built. Editing apps, converters and social platforms build files differently and leave their own fingerprints. Forensics reads those fingerprints and tells you whether a file looks like it came straight out of a phone's camera in one take, was exported or converted afterwards, or was assembled from several clips — and shows you every clue it used, so you can disagree.

Technically: a structural analysis of the container (MP4/MOV atoms), the codec bitstream, the capture metadata and the sample timeline, compared against reference profiles of what iPhone / Android camera apps write versus what libavformat-based tools (ffmpeg, CapCut, HandBrake, web converters) and NLEs write. Each observation is an evidence item with a direction (camera / edited / stitched) and a weight; the verdict is the weighted balance. No pixels are judged — this is complementary to the frame/audio pass and to the AI review.

Turn it on with Add Forensics before a run, or Run Forensics from a finished report. Attaching phone data turns it on automatically.

What you seeIn plain termsTechnically
Combined scoreOne 0–100 number for “does this file behave like raw, untouched footage?” High = consistent with a raw capture; low = clear signs of handling after capture.0.6 × provenance score + 0.4 × the frame/audio authenticity stage (duplicate-frame runs, abrupt histogram cuts, audio RMS jumps). Provenance score = 60 + Σcamera − Σedited − Σstitched weights, clamped.
VerdictCamera-original: looks like it came straight off the phone. Exported: someone ran it through an app or converter (not necessarily faked — messaging apps do this). Stitched: cut together or edited on a timeline. Indeterminate: not enough structure left to say.Class from the weight balance: stitched ≥ 20 → stitched; edited ≥ 18 and > camera → exported; camera ≥ 25 with ≤ 10 against → camera-original; with a high / medium / low confidence from the margin.
Evidence listEvery clue, green for “camera”, amber for “edited”, red for “stitched”, with how much it counted. Read these, not just the number.Each item: id, direction, weight (4–30), finding, raw detail (in the JSON export). Neutral observations are listed separately and carry no weight.
Device profileThe file says “I am an iPhone 13 on iOS 16.2” — so we check whether it still carries everything an iPhone actually writes. Missing pieces mean it was rebuilt by something else on the way to you.Per-family expectations. Apple: qt   brand, Core Media handlers, com.apple.quicktime.* capture keys (make/model/software/creationdate/ISO6709/lens), ≥1 mebx timed-metadata track, iOS-version Software. Android: ISO brand, MediaMuxer VideoHandle/SoundHandle handlers, com.android.version, ©xyz location, Samsung sefd.
Container & encoderHow the file is packaged and which encoder wrote the video. A phone's hardware encoder is silent; ffmpeg, CapCut, HandBrake and friends sign their work.Pure-Python atom walk: ftyp brand + compatible brands, top-level atom order, moov placement (faststart = re-muxed), track handler names, sample-entry vendor/compressor, udta/keys. ffprobe for codec/profile/level/pix_fmt/vendor_id/encoder tags. A 2 MB scan of mdat for x264/x265/Lavc/HandBrake SEI strings.
TimelineCameras keep a very steady rhythm (a keyframe every second, audio and video the same length). Editors start a fresh keyframe at every cut and often leave audio and video slightly different lengths.stts sample-duration runs (distinct deltas, regularity), stss keyframe cadence (mean, min/max, coefficient of variation), elst edit lists, A/V track duration gap, and splice candidates — abrupt scene cuts from the frame pass that coincide (±0.25 s) with a keyframe.
PhotosThe same idea for stills: does it carry the camera's own notes (exposure, lens, maker data), or was it saved by an editor, screenshotted, or stripped?Make/Model, manufacturer MakerNotes count, exposure tags (ExposureTime/FNumber/ISO…), iOS-version Software, XMP history / Photoshop IRB, JFIF-without-EXIF, PNG, HEIC-from-Apple, UserComment “Screenshot”.
Phone-side dataIf you attach what the phone itself recorded, we check it against the file: was the phone where the file says, at that time? Does the photo library agree about when and on what device it was taken? Is the uploaded file byte-for-byte the copy in your export, or was it edited in Photos?Bundle (zip or files) expanded and classified. GPS/sensor tracks → telemetry correlation (position at capture vs file GPS, ≤150 m; capture inside the track window). Google Takeout JSON → photoTakenTime / geoData / deviceType vs file. Apple .AAE → adjustment record (edited in Photos). XMP → edit history. Same-named media in the bundle → SHA-256 compared with the upload.
Frame & audio passThe older authenticity check, folded in: frozen frames, hard cuts, audio jumps, and editing-software names in the metadata.~5 fps grayscale MSE duplicate runs, Bhattacharyya histogram distance ≥ 0.5 for cuts, librosa RMS ratio ≥ 3× for audio jumps, editor-name match (CapCut, Lavf/Lavc, x264, Premiere, Resolve, TikTok, Instagram…; iOS-version strings exempt).
What it can tell you
  • Whether the file is consistent with an unmodified capture from the device family it claims (iPhone-class, Android-class).
  • Whether it was re-encoded, converted or re-muxed after capture — and often by what.
  • Whether it shows the marks of timeline editing or multi-clip assembly, and roughly where the splices are.
  • With phone data: whether the device's own records agree with the file about where, when and on what it was recorded, and whether your upload is the library original.
What it cannot
  • Prove a file came from one specific phone. That needs the device (sensor-noise references or its Photos database) — the domain of device-forensics tools, not a file upload.
  • Tell “exported” from “faked”: WhatsApp, iMessage-compress, AirDrop-convert and Photos all re-export without changing what was filmed.
  • Catch a lossless re-wrap that preserved every marker, or a forger who rebuilt every marker by hand.
  • Judge the picture itself — that is the frame/audio pass, the mundane-object checks and the AI review.
Look closer

The Viewing Lab & enhanced renders

  • Filters — frame differencing, background modeling, gain/gamma, with a wipe to compare against the original.
  • Zoom & pan — get close to small objects; the report's motion events are marked on the seek bar so you jump straight to the action.
  • Ask about this frame — sends the exact frame you're looking at into Evidence Chat.

Enhanced renders are the heavy, server-side versions — frame-accurate mp4s you can replay and download: true background subtraction (moving things in color on black), temporal median (everything static vanishes; transients glow), and a track & stabilize crop that follows the main moving object. Roughly a minute of render per minute of footage; results attach to the case when you file.

AI clarity is the fourth render, for footage too grainy or low-res to read: a temporal denoise pass followed by a neural 4× super-resolution network, either on the full frame (10 s window, pick the start time) or following the object (15 s window, tracked from the box you drew in Speed & direction). A grain-removal slider blends between texture-preserving and heavy-noise weights, and a night boost (auto on dark clips) averages each frame with its aligned neighbours — a software long exposure that recovers real signal from dark footage — then lifts the exposure. It runs a network per frame on CPU, so expect several minutes; a progress bar tracks it. It is an interpretation, not evidence — the network reconstructs plausible detail — and every render is labeled as such.

Kinematics

Speed & direction

The honest physics, up front: a single camera measures angles, not distance — and speed is angular rate × distance. The lab measures the angles exactly, then makes the distance question explicit instead of hiding it. Every speed figure you see carries its anchor.
1
Select. Hit Select object to track (or tap a suggested motion moment). Scrub to a point where the object is clearly visible — early in the sighting, not the end — pause, and drag a tight box around the object itself, not the whole region. Tracking runs forward from that frame.
2
Set the camera context (all optional, all unlock more). Field of view (68° ≈ phone main lens), camera tilt, and camera facing. Don't know your facing? Hit ☀ Calibrate facing from the sun and tap the sun in the frame — the astronomy engine knows exactly where it was and locks your compass.
3
Track. The server follows the object frame-by-frame with camera-shake compensation and replays your clip with the path drawn on it. You get angular rate (mean/peak °/s), direction in frame, angular size trend (growing = approaching), and flagged flight-behavior anomalies — instantaneous reversals and acceleration steps that birds, aircraft, and balloons don't produce.
4
Anchor the distance. Drag the “If it was at…” slider and watch implied speed and implied size update, with Bird / Drone / Balloon / Aircraft plausibility chips lighting up or striking out. One glance answers “what would it take for this to be a bird?”
5
Go geographic. With a camera position (from your resolved place & time, or the telemetry track) plus a facing, the panel shows the object's true compass bearing on a range-ring map, casts the sightline over real terrain elevation data, lists live aircraft on that bearing, and — for drone footage with an SRT log — solves the full triangulation: range, ground speed, and heading.
Generative

AI interpretation — Clarity & Reconstruction

Not evidence, and labeled that way everywhere. Generative models invent detail. These tools produce interpretations for study and communication — the original upload remains the only evidentiary record.
  • Clarify frame — for grainy or compressed media, a Pro-tier image model renders a sharpened, denoised interpretation of the frame you pick. You get two independent renders beside the original on purpose: where the two disagree, the model is guessing.
  • Reconstruct as video — generates a short clip of the sighting, seeded by the clarified frame and driven by the measured motion from your kinematics track. Useful for showing others what the witness experienced.
Make it permanent

Filing a sighting

When the analysis is yours — you shot it, you were there — File it → sends the complete evidence bundle into the review queue: your narrative, when & where, the full forensic report, the Evidence-Chat transcript, the media itself, your telemetry file, any enhanced renders, the kinematics track, and up to 8 additional photos/videos from the same incident (files you multi-selected at upload are already staged).

You get a submission number immediately. Review is human-gated: nothing enters the master archive without a person approving it. Cleared cases become permanent records with their own case number — on the public map's Community cases layer, in the database, in AI search, and citable. Your contact email is never published; pending cases are never shown publicly.

Part 2 · /workbench

The Workbench

Your persistent research workspace. Where Analyze is one file, one report, one sitting — the Workbench is a case file you build over time: multiple pieces of footage, your own field notes, and a submission path to the review desk. Research subscription required; you get 5 GB of evidence storage.

Building a case

1
Create a case. From the library, start a new case file. Give it a title and fill in the sighting details: when it happened, where (free text plus map coordinates), what you think it was, field notes, and tags for organizing your library.
2
Attach footage — as much as you have. Upload every clip and photo from the incident into the same case. Uploads run in parallel with live progress; everything is stored against your 5 GB allowance.
3
Analyze each piece. Hit Analyze on any media card to run it through the full lab — same pipelines as Part 1 — and the report is saved on that media row, permanently. Come back next week and it's still there. Analyze every angle; the reports sit side by side in the case.
4
Watch the timeline. Each case keeps a running timeline — created, media added, analyses completed, status changes — so a case you built over a month reads like a log.
5
Submit the strong ones. When a case has the goods — clean footage, solid context, reports that don't collapse into “airliner” — submit it to the review desk. Drafts stay editable; submitted cases lock while a human reviews.
draftsubmittedunder reviewincorporated

A reviewer routes approved material where it earns a place: the case database, the public map, the story/film pipeline, or the classifier training set — and can also return a case with notes. Incorporation into the master archive is always human-approved, never automatic.

Choosing

Which tool, when

AnalyzeWorkbench
ShapeOne sitting: upload → report → optionally filePersistent case files you build over time
Media per case1 analyzed + up to 8 attached at filingUnlimited within your 5 GB, each analyzable
Reports persist?For the session (and forever if you file)Saved on every media row, always
Best for"What is this clip?" — fast forensic answers, witnesses filing a sightingOngoing investigations, multi-angle incidents, researchers curating a library
Path to the archiveFile this sighting → review queueSubmit case → review desk → routed to database / map / story / training
Access1 free analysis, then ResearchResearch
Reference

Limits & formats

Media

≤ 500 MB per file · images PNG / JPG / WebP / BMP / TIFF · video MP4 / MOV / WebM / MKV / M4V / AVI. Long videos are fine — big files queue and the progress bar keeps reporting.

Phone data

One file, several, or a zip (≤ 400 MB) · tracks: GPX, DJI SRT, CSV/TSV sensor logs (columns matched by name), JSON / GeoJSON, KML · records: Google Takeout JSON, Apple .AAE, XMP, plist · media copies inside a bundle are byte-compared to the upload. If your device's format doesn't parse, send us a sample.

Downloads

Every report exports as Web (HTML), PDF, Markdown, or raw JSON — full report or any single section.

Tiers

Free: one full analysis, the sample, public archive. Research ($5/mo): unlimited analyses, Workbench + 5 GB, enhanced renders, object tracking, AI interpretation, semantic search, proximity atlas — and it keeps the public archive free.

Honesty notes — read once
  • The authenticity and Forensics scores are structural provenance, not deepfake detection. Forensics shows consistency with a device family, never proof that one particular phone recorded the file; “exported” is not “faked”.
  • “Unknown” means not a confident match to anything we know — read it alongside the mundane checks, the sky, and the traffic before it means more.
  • Every speed figure is conditional on a distance anchor; the UI never prints an unconditional number.
  • AI Clarity/Reconstruction outputs and the AI clarity render are generative interpretations — never evidence.
  • Nothing enters the master archive without human review.