Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-04-15
Score updated: 2026-04-15
Score fresh until: 2026-05-15
References: 0
Source count: 3
Coverage: 50%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers | Route /signal-canvas/not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers",
    "query_text": "Summarize Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers",
  "normalized_query": "2604.11508",
  "route": "/signal-canvas/not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers",
  "paper_ref": "not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 0

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

PDF: https://arxiv.org/pdf/2604.11508v1

Source count: 3

Coverage: 50%

Last proof check: 2026-04-15T16:47:41.845Z

Signal Canvas receipt window

Watch and verify: Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

/buildability/not-all-forgetting-is-equal-architecture-dependent-retention-dynamics-in-fine-tuned-image-classifiers

Watchwatch

Subject: Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface