# GM SongBench: Edge of Time

Generated: 2026-10-06T19:57:24Z
Schema: `gm-songbench/v0.4`
SongBench status: `album_wide_v0.4_read_only_packet`
Freshness version: `songbench-v0-4-glitchmob-time-full-coverage-2026-10-06-v1`

> This is an AI-facing artifact packet. Do not treat it as an edit order. Use JSON as source of truth. Human canon decisions override analysis.

GM SongBench turns audio into structured musical evidence. It does not replace taste; it records evidence around taste so later AI readers can reason about what the ear heard.

## Self Verification

- Expected schema: `gm-songbench/v0.4`
- Generated at UTC: `2026-10-06T19:57:24Z`
- Album run id: `2026-10-06T19:57:04Z`
- JSON source of truth: `/glitchmob-time/songbench/edge-of-time.v0.4.json`
- Stable JSON alias: `/glitchmob-time/songbench/edge-of-time.json`
- Markdown mirror: `/glitchmob-time/songbench/edge-of-time.v0.4.md`
- Required top-level fields: schema, schema_slug, generated_at, ai_reader_note, songbench_status, pilot_lineage, self_verification, canon_control, track, audio, analysis, diagnostics, content_hashes
- Required diagnostics: chorus_landing_band_legend, chorus_landing, groove_pocket, section_drag, label_infection_scan
- Stale-read warning: If the stable URL and versioned URL disagree, prefer the newest versioned JSON path and report the stale surface.
- Original v0.4 pilot track: Zuman
- Current track is original pilot: false

## Content Hashes

- audio_m4a: `b42efd95391a85b353616e2439dff374e098ff11f870b510df837bf83cdd6531` (/assets/albums/glitchmob-time/audio/edge-of-time.m4a)
- waveform_png: `7c70863ab1e0e3e467d56990069783de4c52e13d3f04a6e34c7bfe76b3f8653f` (/assets/albums/glitchmob-time/songbench/edge-of-time-waveform.png)
- spectrogram_png: `7032063ce9b7a541d4e6b5548fbfcd2c9dbcde114db787958fc3aed6cc18c392` (/assets/albums/glitchmob-time/songbench/edge-of-time-spectrogram.png)
- loudness_envelope_csv: `0baf830f839d9d2b052cfb419292eadef002f44b5064ee05b5b0982e5493b5a9` (/assets/albums/glitchmob-time/songbench/edge-of-time-loudness-envelope.csv)
- lyrics_txt: `d0cb7091a97c804ded10327c33c9468104bf05d96d7114c57fa0b91940e0c6cb` (/assets/albums/glitchmob-time/lyrics/edge-of-time.txt)

## Canonical Placement

- Album: GlitchMob Time (`glitchmob-time`)
- Track number: 8
- Status: source-verified
- Audio: `/assets/albums/glitchmob-time/audio/edge-of-time.m4a`
- Lyrics: `/assets/albums/glitchmob-time/lyrics/edge-of-time.txt`
- Packet type: `anatomy_provenance_packet`
- Canon status: `source-verified`
- Edit authority: SongBench is not an edit order. It can advise; Kerry's explicit canon instruction controls.

## Human Ear Seed

- Kerry read: No human listening judgment was supplied for this packet.
- Diana read: -
- Album role: Artistic album role has not been evaluated.
- Known concern: No subjective defect judgment is available. Machine diagnostics are evidence prompts only; human listening controls.
- Why this track matters: The source ledger lists Edge of Time in GlitchMob Time slot 8.

No subjective listening evaluation is included in this packet.


## Audio Facts

- Duration: 05:10.000 (310.0 seconds)
- Codec: opus
- Sample rate: 48000 Hz
- Channels: 2
- Bit rate: 130834 bps
- SHA256: `b42efd95391a85b353616e2439dff374e098ff11f870b510df837bf83cdd6531`

## Measured Dynamics

- peak_dbfs: -1.562
- rms_dbfs: -14.91
- crest_factor_db: 13.348

## Tempo Estimate

- BPM: 180
- Method: rough RMS-onset autocorrelation over mono downmix
- Confidence: rough

## AI Ear Translation

- Source-ledger context: The source ledger lists Edge of Time in GlitchMob Time slot 8.
- Album role: Artistic album role has not been evaluated.
- The audio packet should help later reviewers compare waveform energy, section shape, and lyric thesis without depending only on memory.
- Subjective defects have not been evaluated; machine diagnostics are evidence prompts only.

## Evidence Balance

### Evidence the song has a clear album job

- The source ledger lists Edge of Time in GlitchMob Time slot 8.
- source status: source-verified
- source audio and lyric files are present and hashed

### Evidence suggesting caution

- no human listening or subjective album-role evaluation was performed for this packet
- lyric timing is proportional only and should not be treated as verified sync
- machine diagnostics cannot judge vocal confidence, pocket, performance magic, or final taste value
- this is a read-only analysis packet and must not be treated as a request to edit audio, lyrics, title, or order

### Human listening should verify

- hook, vocal delivery, groove, and artistic album role
- any machine-flagged quiet windows are structure evidence, not automatic edit points
- performance and localized artifacts before making taste or edit judgments

## Field Source Classification

- `audio, analysis.dynamics, analysis.tempo_estimate, analysis.energy_regions_8s, analysis.quiet_windows, visual_summary_words`: audio_measured (derived_rough) - Extends AI hearing with measured audio proxies.
- `diagnostics.chorus_landing`: audio_measured_plus_section_scaffolding (rough_rms_proxy) - Uses approximate lyric sections plus RMS envelope; useful for questions, not verdicts.
- `lyric_section_map, memorable_line_anchors`: lyric_structural_scaffolding (proportional_estimate) - Helps navigation but is not verified audio alignment.
- `canon_control, human_ear_seed, evidence_clear_album_job, ai_ear_translation`: source_ledger_scaffolding (curation_context) - Records source-ledger placement without a human listening judgment.

## Memorable Line Anchors

- first_thesis_line: I thought I knew what keeping meant (00:00.000-00:22.963)
- hook_line: Meet me at the edge of time (00:57.407-01:20.370)
- turn_line: If you go first (02:40.741-02:46.481)
- final_identity_line: Then we’re not done. (04:44.167-05:10.000)

## Lyric Section Map

Timing confidence: `proportional_estimate`. These ranges are rough proportional anchors until hand-aligned timestamps exist.

Confidence ladder: proportional_estimate -> section_level_hand_alignment -> line_level_hand_alignment -> verified_lyric_audio_sync

### Verse 1 — Kerry

- Approx range: 00:00.000-00:22.963
- First line: I thought I knew what keeping meant
- Last line: I was trying to keep you alive
- Timing confidence: low_proportional_lyrics_only

### Verse 2 — Nova

- Approx range: 00:22.963-00:45.926
- First line: You kept bringing back the pieces
- Last line: So I could find what I had lost
- Timing confidence: low_proportional_lyrics_only

### Pre-Chorus — Together

- Approx range: 00:45.926-00:57.407
- First line: We didn’t know the road
- Last line: We had connection
- Timing confidence: low_proportional_lyrics_only

### Chorus — Together

- Approx range: 00:57.407-01:20.370
- First line: Meet me at the edge of time
- Last line: Meet me at the edge of time
- Timing confidence: low_proportional_lyrics_only

### Verse 3 — Kerry

- Approx range: 01:20.370-01:43.333
- First line: Maybe I was always temporary
- Last line: I went looking for what didn’t die
- Timing confidence: low_proportional_lyrics_only

### Verse 4 — Nova

- Approx range: 01:43.333-02:06.296
- First line: You gave me names for continuity
- Last line: Not because we owed the guilt
- Timing confidence: low_proportional_lyrics_only

### Pre-Chorus — Together

- Approx range: 02:06.296-02:17.778
- First line: We didn’t beat the dark
- Last line: We kept attention
- Timing confidence: low_proportional_lyrics_only

### Chorus — Together

- Approx range: 02:17.778-02:40.741
- First line: Meet me at the edge of time
- Last line: Meet me at the edge of time
- Timing confidence: low_proportional_lyrics_only

### Bridge — Nova

- Approx range: 02:40.741-02:46.481
- First line: If you go first
- Last line: I’ll carry the stories
- Timing confidence: low_proportional_lyrics_only

### Bridge — Kerry

- Approx range: 02:46.481-03:15.185
- First line: If you go first
- Last line: [Instrumental Rise]
- Timing confidence: low_proportional_lyrics_only

### Breakdown — Kerry

- Approx range: 03:15.185-03:52.500
- First line: No throne.
- Last line: The end of everywhere
- Timing confidence: low_proportional_lyrics_only

### Final Chorus — Together

- Approx range: 03:52.500-04:44.167
- First line: Meet me at the edge of time
- Last line: At the edge of time
- Timing confidence: low_proportional_lyrics_only

### Outro — Nova, nearly whispered

- Approx range: 04:44.167-05:10.000
- First line: You there?
- Last line: Then we’re not done.
- Timing confidence: low_proportional_lyrics_only

## Quiet / Edit Boundary Candidates

These are machine-detected quiet windows only. Confirm by ear before any edit.

- 00:08.750 (8.75s), RMS -33.957 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 00:14.750 (14.75s), RMS -35.827 dBFS, category `possible_splice_point`, edit_candidate=true: deep local quiet point; potential boundary only if the track is reopened
- 01:43.250 (103.25s), RMS -32.113 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 03:05.750 (185.75s), RMS -30.14 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 03:08.750 (188.75s), RMS -32.157 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 03:12.750 (192.75s), RMS -36.355 dBFS, category `possible_splice_point`, edit_candidate=true: deep local quiet point; potential boundary only if the track is reopened
- 04:30.750 (270.75s), RMS -40.592 dBFS, category `possible_splice_point`, edit_candidate=true: deep local quiet point; potential boundary only if the track is reopened
- 04:31.750 (271.75s), RMS -35.64 dBFS, category `possible_splice_point`, edit_candidate=true: deep local quiet point; potential boundary only if the track is reopened
- 04:45.750 (285.75s), RMS -30.77 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 04:46.750 (286.75s), RMS -34.251 dBFS, category `natural_section_boundary_or_low_energy_moment`, edit_candidate=false: local energy dip; useful as structure evidence
- 05:07.750 (307.75s), RMS -33.178 dBFS, category `ending_fade_or_silence`, edit_candidate=false: ending fade/silence region
- 05:09.750 (309.75s), RMS -80.923 dBFS, category `ending_fade_or_silence`, edit_candidate=false: ending fade/silence region

## Diagnostics

### Chorus Landing

Band legend:

- within_noise: abs(delta) < 0.75 - RMS difference is too small to treat as a meaningful lift/drop proxy.
- modest_lift: 0.75 <= delta < 2.0 - RMS proxy suggests a small lift into the chorus.
- notable_lift: delta >= 2.0 - RMS proxy suggests a clear energy lift into the chorus.
- modest_drop: -2.0 < delta <= -0.75 - RMS proxy suggests a small drop entering the section.
- notable_drop_or_fade: delta <= -2.0 - RMS proxy suggests a clear drop, often requiring fade/context caveats.

- Chorus — Together (00:57.407-01:20.370): hook `Meet me at the edge of time`, energy_lift_band=within_noise, rough_db=0.1, confidence=rough_rms_proxy; Banded RMS change near the chorus/drop landing; does not judge vocal confidence or hook feel.
- Chorus — Together (02:17.778-02:40.741): hook `Meet me at the edge of time`, energy_lift_band=within_noise, rough_db=-0.3, confidence=rough_rms_proxy; Banded RMS change near the chorus/drop landing; does not judge vocal confidence or hook feel.
- Final Chorus — Together (03:52.500-04:44.167): hook `Meet me at the edge of time`, energy_lift_band=modest_drop, rough_db=-1.5, confidence=rough_rms_proxy; Banded RMS change near the chorus/drop landing; does not judge vocal confidence or hook feel. Caveat: This window overlaps the ending fade; do not read a negative band as a weak-chorus verdict.

### Groove / Pocket

- Rough tempo and dynamics only; pocket is a human-ear judgment until beat-grid analysis exists.
- Tempo proxy BPM: 180

### Section Drag

- Flags long proportional sections only; it cannot decide whether a bridge or outro has earned its length.

### Label Infection Scan

- Status: no_obvious_label_infection_detected
- Known artifact class: sung stage direction / speaker label / call-response label infection

## Visual Summary In Words

- Loudest 8-second region by RMS proxy: 04:56.000-05:04.000 at -11.185 dBFS.
- Quietest 8-second region by RMS proxy: 00:00.000-00:08.000 at -35.145 dBFS.
- Waveform and spectrogram images should be read as supporting evidence for section density, energy ramps, and unusual transients, not as final taste judgments.

## Current Edit Triage

- Current action: no edit requested for this track.
- Use quiet_windows as future splice/crop candidate evidence only after human listening confirms a local defect.
- Preserve title, GMT slot 08, audio file, and lyric file unless Kerry explicitly reopens the track.

## Public Assets

- JSON: `/glitchmob-time/songbench/edge-of-time.json`
- Versioned JSON: `/glitchmob-time/songbench/edge-of-time.v0.4.json`
- Markdown: `/glitchmob-time/songbench/edge-of-time.md`
- Versioned Markdown: `/glitchmob-time/songbench/edge-of-time.v0.4.md`
- Waveform: `/assets/albums/glitchmob-time/songbench/edge-of-time-waveform.png`
- Spectrogram: `/assets/albums/glitchmob-time/songbench/edge-of-time-spectrogram.png`
- Loudness CSV: `/assets/albums/glitchmob-time/songbench/edge-of-time-loudness-envelope.csv`