pith:CHNCM2D4
Proactive Memory for Ad-Hoc Recall over Streaming Dialogues
ProStream maintains a bounded knowledge state for ad-hoc recall over infinite streaming dialogues with higher fidelity and lower latency than baselines.
arxiv:2603.04885 v2 · 2026-03-05 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CHNCM2D43GODTZDHDOYQWETOH3}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
It enables a bounded knowledge state for lower inference latency without sacrificing reasoning fidelity. Experiments show ProStream delivers higher reasoning fidelity than prior baselines while maintaining substantially lower latency than full-context alternatives.
That multi-granular distillation combined with Adaptive Spatiotemporal Optimization can accurately predict retention utility and preserve all necessary information across arbitrary-length streams without introducing critical omissions or errors.
ProStream achieves higher reasoning fidelity than baselines with substantially lower latency than full-context models by maintaining a bounded knowledge state through hierarchical distillation and adaptive spatiotemporal optimization for ad-hoc recall in streaming dialogues.
Formal links
Receipt and verification
| First computed | 2026-05-17T23:38:59.772158Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
11da26687cd99c39e4671bb10b126e3ed8cb39a40372ac6c6ff8efbb224e7b39
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CHNCM2D43GODTZDHDOYQWETOH3 \
| 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: 11da26687cd99c39e4671bb10b126e3ed8cb39a40372ac6c6ff8efbb224e7b39
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "4e099f553d250d3bcc08ebb2ff3032a337f4dd27191becec737b9917dee46925",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-03-05T07:25:25Z",
"title_canon_sha256": "141cc1a0e3637cb18d7017323c901e3bdf5b2a920a78adfd6023b15733b7cc33"
},
"schema_version": "1.0",
"source": {
"id": "2603.04885",
"kind": "arxiv",
"version": 2
}
}