Pith Number

pith:MTQBGLQE

pith:2026:MTQBGLQED3QCLRXLCL4WDREZTR

not attested not anchored not stored refs resolved

Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis

Fandi Sun, Haoyu Wen, Yijin Wang

Projecting ABSA features into complex space via zero-initialized residuals separates opposing polarities by phase.

arxiv:2603.28205 v2 · 2026-03-30 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MTQBGLQED3QCLRXLCL4WDREZTR}

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

Our framework achieves a state-of-the-art Macro-F1 score of 0.8923 on the ASAP dataset, outperforming robust baselines by projecting textual features into a complex semantic space and using an anti-collision mask to expand the discriminative margin between opposing polarities.

C2weakest assumption

That mapping features to complex space via zero-initialized residual projection plus the masked angle loss will reliably isolate polarities and generalize beyond the ASAP dataset without introducing new representation artifacts or requiring extensive hyperparameter tuning.

C3one line summary

Zero-Initialized Residual Complex Projection with anti-collision masked angle loss reaches 0.8923 Macro-F1 on the ASAP dataset for aspect-based sentiment analysis.

References

22 extracted · 22 resolved · 0 Pith anchors

[1] Issues and challenges of aspect-based sentiment analysis: A comprehensive survey 2020

[2] Survey on aspect-level sentiment analysis 2015

[3] Contrastive sentence representation learning with adaptive false negative cancellation 2024

[4] QPEN: quantum projection and quantum entanglement enhanced network for cross-lingual aspect-based sentiment analysis 2024

[5] Encoding word order in complex embeddings 1912

Receipt and verification

First computed	2026-05-17T23:39:15.636083Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

64e0132e041ee025c6eb12f961c4999c7e4d6632e26f5dc7fa6cc99ad19c1f08

Aliases

arxiv: 2603.28205 · arxiv_version: 2603.28205v2 · doi: 10.48550/arxiv.2603.28205 · pith_short_12: MTQBGLQED3QC · pith_short_16: MTQBGLQED3QCLRXL · pith_short_8: MTQBGLQE

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/MTQBGLQED3QCLRXLCL4WDREZTR \
  | 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: 64e0132e041ee025c6eb12f961c4999c7e4d6632e26f5dc7fa6cc99ad19c1f08

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "38b4ca2705328cf68bc1eec0e2ed3d101db3d8d9faa18e6469ceb0004cf5c6fd",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-03-30T09:23:04Z",
    "title_canon_sha256": "a85b65a6cc9dfda79db44473b9c3f04513b61d81abf11c5a98b2276fbf0af860"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.28205",
    "kind": "arxiv",
    "version": 2
  }
}