Pith Number

pith:4P7MDSIT

pith:2026:4P7MDSIT6Z65IQUOGKLMAQ7FLM

not attested not anchored not stored refs resolved

ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis

Ali Khodabandeh Yalabadi, Ivan Garibay, Mohammad Jahid Ibna Basher, Ozlem Ozmen Garibay

Dual encoders with EMA stabilization lift template-based retrosynthesis top-1 accuracy from 50.5% to 62.4% on USPTO-50k.

arxiv:2605.12736 v1 · 2026-05-12 · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4P7MDSIT6Z65IQUOGKLMAQ7FLM}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On the local USPTO-50k benchmark, Stage 2 candidate set ranking improves top-1 reaction accuracy from 50.5% to 61.3%, while EMA stabilized template adaptation further improves it to 62.4%. Fine tuning from a leakage controlled USPTO-Full checkpoint reaches 75.4% top-1 accuracy on USPTO-50k.

C2weakest assumption

The contrastive pretraining produces a shared embedding space in which nearest-neighbor retrieval over templates meaningfully corresponds to chemically valid reactant predictions, and that the mined hard-negative sets remain stable under the EMA update without introducing systematic bias.

C3one line summary

ConRetroBert achieves 62.4% top-1 accuracy on USPTO-50k by combining contrastive pretraining, hard-negative listwise ranking, and EMA-stabilized dual encoders for template retrieval in retrosynthesis.

References

28 extracted · 28 resolved · 0 Pith anchors

[1] Chemistry--A European Journal , volume= 2017

[2] ACS central science , volume= 2017

[3] Digital Discovery , volume= 2024

[4] Nature Communications , volume= 2023

[5] Nature Communications , volume= 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:49.155711Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e3fec1c913f67dd4428e3296c043e55b3715588b3027ac82d80cab444c15cd16

Aliases

arxiv: 2605.12736 · arxiv_version: 2605.12736v1 · doi: 10.48550/arxiv.2605.12736 · pith_short_12: 4P7MDSIT6Z65 · pith_short_16: 4P7MDSIT6Z65IQUO · pith_short_8: 4P7MDSIT

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/4P7MDSIT6Z65IQUOGKLMAQ7FLM \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: e3fec1c913f67dd4428e3296c043e55b3715588b3027ac82d80cab444c15cd16

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "54a9d32132385b6400d4ac8826ecedf7ac497fa79384c7224f84a9cb052cb387",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T20:40:22Z",
    "title_canon_sha256": "679db2f59def5caefe5cf8462f1096504cc977f8d44a03440bb1294497a466e8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12736",
    "kind": "arxiv",
    "version": 1
  }
}