Pith. sign in

Paper Citation Record · LEDGER

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication

As of 1 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.01601.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.01601 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-03T14:55:01.461263Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-31T06:34:12.847434+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

15 of 15 outbound references displayed

  • verified exact2
  • verified fuzzy13
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ccdaa5bb-2c7f-417d-9df2-1b21e723ee90 · outbound

This paper cites Deduplicating training data makes language models better,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Deduplicating training data makes language models better,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.110162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:f634b1013bb34ace9c1cfd0dbcc09622967a3bfdb17d875491fb1eb0a25c76e2

Observation 8cb3ff0d-32b6-4d26-8e39-8da77539c3d5 · outbound

This paper cites Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learning.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learning

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-07-03T14:58:32.431573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:77fd328157a397091a1c9d43899a8c93e97a3a3bdcbce22864b0c8de7ca6a90f

Observation ff9dd30a-140b-4017-a939-945bf0fe70f5 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-07-03T14:58:32.429099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:371bbb877d5358432bf72356c368e443e43e0091775669ffb89b33faae4f30d0

Observation 80f28b9b-dbf7-4bd4-bff8-1c94314f4e50 · outbound

This paper cites A unified inference optimization framework for qwen3-vl-2b- instruct.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication A unified inference optimization framework for qwen3-vl-2b- instruct

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.108208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:32d0f3efeef04f8d1af95b8cc64f1f4a8da83b06ef89eb69158c1d6c0932d8ba

Observation 5a9355f5-9278-49e6-9e81-c2d20314dd4b · outbound

This paper cites Dolma: An open corpus of three trillion tokens for language model pretraining research,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Dolma: An open corpus of three trillion tokens for language model pretraining research,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.112153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:c5a2de775cc5999f39e2d62351105324eaef6b9253e1a6377070af85b8943508

Observation dc129b16-6bfa-477c-a93b-81fc47122c90 · outbound

This paper cites Coil: Revisit exact lexical match in information retrieval with contextualized inverted list,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Coil: Revisit exact lexical match in information retrieval with contextualized inverted list,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.091874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:1fae1d016155054d8fdaf974bf07ff668f4335c64abe11490c29cb567fbfa003

Observation 11d84dad-e375-491d-b0ed-f3fcc6993429 · outbound

This paper cites Colbertv2: Effective and efficient retrieval via lightweight late interac- tion,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Colbertv2: Effective and efficient retrieval via lightweight late interac- tion,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.100990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:8df4139cf113e1eb6f4b52667763345c445f48f5e4973111328da773d2247bcb

Observation d14a07ea-0697-4e4d-8a38-63828bd36055 · outbound

This paper cites Simcse: Simple contrastive learning of sentence embeddings,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Simcse: Simple contrastive learning of sentence embeddings,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.104441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:62281a2978bde4da49793b9b9af168deead52f6f33a298619c9def6013106bef

Observation 1dfce930-6a19-45ca-8e2b-1fe37a4eec6b · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.097276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:30e3844ab81377353962016dc5c54608ffb1a75defaec918f5258a8b42ca1a5f

Observation 8f368e04-3541-433e-96ea-8af9e5432c82 · outbound

This paper cites G-eval: Nlg evaluation using gpt-4 with better human alignment.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication G-eval: Nlg evaluation using gpt-4 with better human alignment

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.095265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:6abaa7af78c94aec181c1879793e820168f9eaf6d785f0c869b8aee40ef143f3

Observation 2855dc5a-ccc8-4457-81d4-c9192c10551d · outbound

This paper cites Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.099072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:259052896c4bc97457dbf106c4ed913aa75d8eefc5da6e01eeb750dbb7db4361

Observation f36d8feb-f957-4960-b33c-4029b66d4c2f · outbound

This paper cites Prism: Pipeline for root-cause investigation via specialized multi-agents,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Prism: Pipeline for root-cause investigation via specialized multi-agents,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.102786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:e8015dfafb4c89b5fc601ba0a18d0711235465a48bb76016c40ca4f27cb2d8b3

Observation 3df2a1c9-0469-492e-bc94-ef99106b3ddb · outbound

This paper cites Dynarag: Bridging static and dynamic knowledge in retrieval-augmented genera- tion,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Dynarag: Bridging static and dynamic knowledge in retrieval-augmented genera- tion,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.106452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:9d47ebac4229e021aff2d597874682cbbacce54257cd0852052a7d886d63da94

Observation ddaefa33-dd35-4606-92e0-8dfd10acfdb9 · outbound

This paper cites Pyramid convolution and bidirectional graph attention for cyber threat detection from unstructured text,.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Pyramid convolution and bidirectional graph attention for cyber threat detection from unstructured text,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.113883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:cd80f5d0f65b4db04c42b3ae991b21d2bef87394ab1586db0d129e5c56cb8e06

Observation 2e5749a1-58b5-4f31-b766-a03cbfd562ff · outbound

This paper cites Roofline-guided mixed quantization and kernel co- optimization for efficient large language model inference on arm cpus.

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication Roofline-guided mixed quantization and kernel co- optimization for efficient large language model inference on arm cpus

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-07-05T06:40:46.093545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

source=pdf_text observed=2026-07-03T14:55:01.461263Z digest=sha256:d4769196f8bd362516865b2c65e3133b641291ad30b82cb0e3634df48aeef768

Pith citing papers

No inbound Pith citation observations are available.