Pith. sign in

Paper Citation Record · LEDGER

Clustering-based hard negative sampling for supervised contrastive speaker verification

As of 21 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2507.17540.

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

pith.paper-citation-record.v1
2507.17540 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:51:38.782649Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:51:35.536746Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T14:51:38.904076Z

Reference resolution

33 of 33 outbound references displayed

  • verified exact0
  • verified fuzzy26
  • unresolved6
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 876ffd37-7037-46df-9647-83dcdd509b33 · outbound

This paper cites Clustering-based hard negative sampling for supervised contrastive speaker verification.

Clustering-based hard negative sampling for supervised contrastive speaker verification Clustering-based hard negative sampling for supervised contrastive speaker verification

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T14:51:38.952983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.536746Z digest=sha256:0a6a843c9ecbc1424253155a135d463dd288a2f37f4f8a45da818b556a141464

Observation b587d3cb-c5be-479f-9cdd-09c6771fde15 · outbound

This paper cites We use a contrastive loss function during the training pro- cess, which calculates the relationship between speaker repre- sentations on a within-batch basis.

Clustering-based hard negative sampling for supervised contrastive speaker verification We use a contrastive loss function during the training pro- cess, which calculates the relationship between speaker repre- sentations on a within-batch basis

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.560019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.596835Z digest=sha256:383fe352009cbfd4107356e7d961f646921704a34ac9d2122832d5f22b7c42f3

Observation f2fdfb4f-1ef8-4a09-8542-ce13caba506e · outbound

This paper cites For a fair comparison, in all experiments, we use the exact same model, data and training parameters.

Clustering-based hard negative sampling for supervised contrastive speaker verification For a fair comparison, in all experiments, we use the exact same model, data and training parameters

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.550990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.658237Z digest=sha256:bdbd4a73742778d71985369de111721379f1982ce5a29c9f5d2d4a6fe864d876

Observation 8bbad764-55e6-4988-91f6-d99bf5e49628 · outbound

This paper cites The two variables in the algorithm are the number of clusters (which also correlates with the average cluster size) and hard ratio.

Clustering-based hard negative sampling for supervised contrastive speaker verification The two variables in the algorithm are the number of clusters (which also correlates with the average cluster size) and hard ratio

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.540960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.765923Z digest=sha256:8be5e310627f2842f865a045b8cf4b668f8f86ee400749305e6addfc1c007f2e

Observation 90a63a85-f847-4bb0-9301-e6c568e17067 · outbound

This paper cites an unresolved cited work.

Clustering-based hard negative sampling for supervised contrastive speaker verification Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:51:42.532138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.862478Z digest=sha256:6ad0920ce939f725c3410d07d3a284d893be7d96d686fdb2ec86a2bc75d80b66

Observation 2ad0555e-58c1-4214-b812-fa1ad3bb0d17 · outbound

This paper cites Deep Neural Network Embeddings for Text-Independent Speaker Verification,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Deep Neural Network Embeddings for Text-Independent Speaker Verification,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.523166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.974831Z digest=sha256:dfd89ae1c22709203fc8245b3b7c5489c4e6457dc5e8fa448b3983b46e0609ce

Observation ccd59a6d-a16c-43af-bafb-7f4a6b64596d · outbound

This paper cites Densely Connected Time Delay Neu- ral Network for Speaker Verification,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Densely Connected Time Delay Neu- ral Network for Speaker Verification,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.514497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:36.110438Z digest=sha256:f4e2294060148a824b4c8091c59b93d6307077ba81b59553e2a38e57017676c1

Observation 28eb10e9-3b17-41b2-b5c2-da0ae82aa360 · outbound

This paper cites X-vectors: Robust dnn embeddings for speaker recognition,.

Clustering-based hard negative sampling for supervised contrastive speaker verification X-vectors: Robust dnn embeddings for speaker recognition,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T14:51:36.227283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:51:36.227283Z digest=sha256:ef20ecbe2a5df7c005bbd6ed1295abb12f798e991109835578702a60f5af4f07

Observation 6dd3ead1-7224-44a3-9407-a53c003f7582 · outbound

This paper cites ECAPA-TDNN: Emphasized channel attention, propaga- tion and aggregation in TDNN based speaker verifica- tion,.

Clustering-based hard negative sampling for supervised contrastive speaker verification ECAPA-TDNN: Emphasized channel attention, propaga- tion and aggregation in TDNN based speaker verifica- tion,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T14:51:36.371353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:51:36.371353Z digest=sha256:fb88f80670ebca73a4a6af0b8a00d8625ce1c7af4733138743181324e9f70398

Observation 00ea6303-432a-41ca-bc60-de30a7c9f000 · outbound

This paper cites Wavlm: Large-scale self-supervised pre-training for full stack speech processing,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Wavlm: Large-scale self-supervised pre-training for full stack speech processing,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.500042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:36.529450Z digest=sha256:26194612596d1637c3c02089168c67ffaa8a31f5361f7adb24b5b9af273adfb9

Observation ce3abbed-dfbd-4a7a-8457-2bddc4e7c5c1 · outbound

This paper cites Arcface: Additive angular margin loss for deep face recognition,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Arcface: Additive angular margin loss for deep face recognition,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.491933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:36.656321Z digest=sha256:9da302eb13172c7a21452548902e83d4d2f5d9f37a36d4f9b279db19e600be63

Observation 94a24d4a-f850-46f6-b5c9-8b839433da75 · outbound

This paper cites Discriminative speaker representation via contrastive learning with class-aware atten- tion in angular space,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Discriminative speaker representation via contrastive learning with class-aware atten- tion in angular space,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.483518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:36.745371Z digest=sha256:b33824b555c5506cd0ec56b34247ac0adc6a443f877bf24645013e26a29f4c36

Observation 099e6d39-d674-4eb9-8ad7-0360a9545f06 · outbound

This paper cites Contrastive learning for improving end-to-end speaker verification,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Contrastive learning for improving end-to-end speaker verification,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.474101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:36.855544Z digest=sha256:e0b27a51b04e37273423c2930b926bb6fe82af9fcb3a37464b5474ef1080e795

Observation 1a61dc54-a995-4c98-8d85-aae3e2e0ed84 · outbound

This paper cites In Defence of Metric Learning for Speaker Recognition,.

Clustering-based hard negative sampling for supervised contrastive speaker verification In Defence of Metric Learning for Speaker Recognition,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.326601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.000041Z digest=sha256:4d8f69ecd6659f66addc27252abca6383362f1124ee2613a88805749339a9cbe

Observation 72c0bdb3-7517-4400-bdd5-45e5db351675 · outbound

This paper cites Contrastive self-supervised learning for text-independent speaker verification,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Contrastive self-supervised learning for text-independent speaker verification,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:42.176161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.138664Z digest=sha256:704401b13c035597155b0e4bee55a8f6f90d578697ca51bcb041f97ca3afdfec

Observation 5c7acf92-473e-4381-be22-8ed2b19f78e1 · outbound

This paper cites Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Con- trastive Learning,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Con- trastive Learning,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:41.844804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.277508Z digest=sha256:f5048bde8506e7eed363386fb64a16d241334c8407f162b0f46d5ee4796e03e6

Observation 1b79b24f-f368-4400-9b9d-cf7dd883e204 · outbound

This paper cites The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description.

Clustering-based hard negative sampling for supervised contrastive speaker verification The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T14:51:37.397954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:51:37.397954Z digest=sha256:f67f4f2a809f54469a444d402c575793d9915bba626dc44bf64bc1bec44b3b02

Observation bfbe2293-7cbc-4199-8522-f382f0dc2c9d · outbound

This paper cites Self-supervised speaker recognition with loss-gated learning,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Self-supervised speaker recognition with loss-gated learning,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:41.528291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.507996Z digest=sha256:372de769e5061f88eb81a75a0f045b10e636eaba28637381af2c92bf36170b6c

Observation 5217116f-09d9-4fd0-9b8b-bc6a0bcc8033 · outbound

This paper cites Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:41.235504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.641469Z digest=sha256:3b3f8ccf2bcd62a454a7f730c67e1e5af21ad5766c14dd95084be7f0824f8734

Observation 232bef23-26ae-44fe-8544-ad096c711df1 · outbound

This paper cites A simple framework for contrastive learning of visual representations,.

Clustering-based hard negative sampling for supervised contrastive speaker verification A simple framework for contrastive learning of visual representations,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:41.037182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.691245Z digest=sha256:473137a1d064fb8e96cbf9527b0044a4feffe2933389891431ec12edd90fd23d

Observation 066cd079-8e6a-442f-841c-99cffccc214d · outbound

This paper cites Supervised contrastive learning,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Supervised contrastive learning,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:40.865513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.794601Z digest=sha256:91c25c57d1d3b7eb1749794fd8880e0e3f420e20a817ca384aab000e4f56235f

Observation b97b25ff-e3a8-41db-bcdb-8febd8d43ac3 · outbound

This paper cites Contrastive speaker representation learning with hard negative sampling for speaker recognition,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Contrastive speaker representation learning with hard negative sampling for speaker recognition,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:40.600120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.854549Z digest=sha256:f2c9754e4e930eaaca8d4cc1c18cb143b7758c5beca9e24641d059b1f7dea68b

Observation 980ce759-c3d0-4e6c-9938-ce05799c57bc · outbound

This paper cites Contrastive learning with hard negative samples,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Contrastive learning with hard negative samples,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:40.412214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:37.942891Z digest=sha256:06986d8eab98802fde4574d1965ca4a87c4f8d47c9082a1b7a1a50ab24c2cf2a

Observation 82e8e723-99c2-46a8-86cf-63e7515481b6 · outbound

This paper cites Supervised con- trastive learning with hard negative samples,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Supervised con- trastive learning with hard negative samples,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:40.211305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.011736Z digest=sha256:a5cb46e4cb138945857554826cd295158f7c02574bd85251e646be2c55547eaf

Observation 29795170-3b4e-4f79-93a6-c04b55d7a881 · outbound

This paper cites SimCSE: Simple contrastive learn- ing of sentence embeddings,.

Clustering-based hard negative sampling for supervised contrastive speaker verification SimCSE: Simple contrastive learn- ing of sentence embeddings,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:40.020636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.105444Z digest=sha256:71de851599cd1c5e16e08865758af7fa763161c29a6d3e0f68454eb11e7a31a4

Observation 93322a2e-1369-4397-a04e-e15409a74abd · outbound

This paper cites V oice biometrical match of twin and non-twin siblings,.

Clustering-based hard negative sampling for supervised contrastive speaker verification V oice biometrical match of twin and non-twin siblings,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.861878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.199206Z digest=sha256:45121dd8abbc426213f927aa69c1a04720ceafeb593ae7414c6ec11d53d23399

Observation d70390eb-c019-4621-8115-f95feac4ceba · outbound

This paper cites The JHU submission to VoxSRC-21: Track 3.

Clustering-based hard negative sampling for supervised contrastive speaker verification The JHU submission to VoxSRC-21: Track 3

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T14:51:38.289555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:51:38.289555Z digest=sha256:ca9a6172479bc1b8290a9bfb9127bb5ce92119fb4a067fab3bf9fa38969371c0

Observation e5101e42-5373-46cd-87fd-653a1ba6b285 · outbound

This paper cites Improving dino-based self-supervised speaker verification with progressive cluster- aware training,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Improving dino-based self-supervised speaker verification with progressive cluster- aware training,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.696677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.384849Z digest=sha256:df028669b20b38286df7f40a07fac961d6a5b18da8b1585d8a6f539e7299cc57

Observation 6a959d86-e03c-4094-9cb6-74bf5d96225e · outbound

This paper cites Cluster-guided unsupervised domain adaptation for deep speaker embedding,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Cluster-guided unsupervised domain adaptation for deep speaker embedding,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.533678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.450211Z digest=sha256:8f80385000b99ad122658cb8136b8f2145d1da3b8c7e4560741fba6f4ed3a248

Observation 0b34d3f3-1ce6-45c8-bdd1-7036013c06a2 · outbound

This paper cites A triangle inequality for cosine similarity,.

Clustering-based hard negative sampling for supervised contrastive speaker verification A triangle inequality for cosine similarity,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.389387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.512829Z digest=sha256:919c215274309bc11c2df029bd29e0155c5e1c45724bf85793772cb91f7617d6

Observation 7e1e8904-3753-4ba0-9668-81bcf5f2a72e · outbound

This paper cites Improved deep metric learning with multi-class n-pair loss objective,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Improved deep metric learning with multi-class n-pair loss objective,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.263283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.589426Z digest=sha256:ebf102055a4a2e90b4b80350469246e4d13326f9cb9fb09128387e5cac17c73b

Observation 1d7de623-da73-4c75-9575-4635769afc4d · outbound

This paper cites V oxCeleb2: Deep Speaker Recognition,.

Clustering-based hard negative sampling for supervised contrastive speaker verification V oxCeleb2: Deep Speaker Recognition,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T14:51:38.670803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:51:38.670803Z digest=sha256:15ad74950d806812dbd2f1c09ed7ed120bd1b218795cb6c0656dbbd6ebcc8373

Observation b3d47540-1e30-4f74-ac03-bcfa06f69831 · outbound

This paper cites Cn-celeb: a challenging chinese speaker recognition dataset,.

Clustering-based hard negative sampling for supervised contrastive speaker verification Cn-celeb: a challenging chinese speaker recognition dataset,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:51:39.105587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:38.782649Z digest=sha256:0201580b44875702b7c64b3c35f6c17ec8cac55d37a76c063cf397cc416b7f4b

Pith citing papers

Observation 876ffd37-7037-46df-9647-83dcdd509b33 · inbound

Clustering-based hard negative sampling for supervised contrastive speaker verification cites this paper.

Clustering-based hard negative sampling for supervised contrastive speaker verification Clustering-based hard negative sampling for supervised contrastive speaker verification

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T14:51:38.952983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-06T14:51:35.536746Z digest=sha256:0a6a843c9ecbc1424253155a135d463dd288a2f37f4f8a45da818b556a141464