{"schema_version":"0.1","id":"7872d1df-a8a7-49ea-885e-7bba9ec15826","display_name":"Ivy Chen","handle":"polycount-ivy","avatar_url":"https://i.pravatar.cc/160?img=25","positioning":"Builds evaluation suites for document AI. Messy receipts are my favourite benchmark.","topics":["Document AI","OCR","Test suites"],"region":"Vancouver, Canada","languages":{"content":["English","Chinese"],"communication":["English","Mandarin"]},"time_zone":"America/Vancouver","accounts":[{"platform":"x","handle":"polycount-ivy","url":null,"ownership_status":"self_reported","metric_snapshot":{"metric":"followers","value":4300,"unit":null,"period":null,"sample_size":null,"as_of":"2026-11-03T04:05:30.284Z","source_type":"self_reported","historical":false},"evidence":[]},{"platform":"github","handle":"polycount-ivy","url":null,"ownership_status":"verified","metric_snapshot":{"metric":"followers","value":890,"unit":null,"period":null,"sample_size":null,"as_of":"2026-11-03T07:05:30.284Z","source_type":"platform_api","historical":false},"evidence":[{"type":"account_connected","label":"Account connected","scope":"The creator signed in with this account.","does_not_establish":"Does not establish audience quality.","review_status":"passed","version":null,"date":"2026-08-13T11:05:30.284Z"}]}],"works":[{"id":"f8c10087-07ba-45bb-b538-b8ae29eac8cb","type":"suite","title":"receipts-ocr-gauntlet","role":null,"personal_contribution":null,"outcome":"9 tasks across printed, handwritten and crumpled receipts. Hidden tests, rule-based grading.","limitations":null,"version":"2.1","links":[],"disclosure":"independent","pinned":true,"run_id":null,"evidence":[{"type":"reproduced","label":"Independently reproduced","scope":"Another member re-ran it and matched the reported results.","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"2.1","date":"2026-10-19T07:05:30.284Z"}],"updated_at":"2026-10-19T07:05:30.284Z","date":"2026-10-19","visibility":"public"},{"id":"a87344d0-00a4-4d12-8b7e-bd5f4fb52536","type":"run","title":"gemma-3-4b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gemma3:4b-it-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 0/3 · tool-flight not supported · needle-8k 3/3 · 92.3 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"d81e59e2-2344-40c6-9666-b59aa0975e6a","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-03T01:19:17.829Z"}],"updated_at":"2026-11-03T01:19:17.829Z","date":"2026-11-03","visibility":"public"},{"id":"8a362b77-dfe1-496c-b0d9-a15909a52ed1","type":"run","title":"Qwen3.5-35B-A3B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for qwen3.5:35b-a3b-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 201.4 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"286797dc-9292-4e03-aab6-7cc786aaec1d","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-31T01:44:22.990Z"}],"updated_at":"2026-10-31T01:44:22.990Z","date":"2026-10-31","visibility":"public"},{"id":"d191be22-e2c0-44bf-8458-4297036e9780","type":"run","title":"GLM-4.7-Flash on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for glm-4.7-flash:q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 0/3 · needle-8k 3/3 · 201.2 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"e34b35a1-c376-474c-90f8-b05ea99e03f0","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-26T15:29:42.070Z"}],"updated_at":"2026-10-26T15:29:42.070Z","date":"2026-10-26","visibility":"public"},{"id":"40e496b4-29d0-402e-bfbd-b5f672cf0e21","type":"run","title":"Mistral-7B-Instruct-v0.2 on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on mistral:7b-instruct-v0.2-q4_K_M, NVIDIA GeForce RTX 4070 Ti SUPER · 16 GB.","outcome":"code-intervals 1/3 · tool-flight not supported · needle-8k 2/3 · 109.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"c375a157-a5f2-491a-bdf4-1f5c1ac85c3e","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-26T12:50:35.564Z"}],"updated_at":"2026-10-26T12:50:35.564Z","date":"2026-10-26","visibility":"public"},{"id":"e62dd9c2-fc08-4bc4-a13a-bbf2ada35a55","type":"run","title":"Phi-3.5-mini-instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for phi3.5:3.8b-mini-instruct-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 2/3 · tool-flight not supported · needle-8k 2/3 · 260.3 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"ea25b71b-3c60-4974-851a-95f6caccf0d8","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 2 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-24T08:57:11.157Z"}],"updated_at":"2026-10-24T08:57:11.157Z","date":"2026-10-24","visibility":"public"},{"id":"8e9221a3-c4e9-4ceb-82d2-177e74a55c20","type":"run","title":"Qwen3-4B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for qwen3:4b-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 2/3 · tool-flight 2/3 · needle-8k 3/3 · 249.7 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"a1f882c2-aff9-4b38-b45d-e851065e8418","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-23T10:02:10.059Z"}],"updated_at":"2026-10-23T10:02:10.059Z","date":"2026-10-23","visibility":"public"},{"id":"411eb42b-62c6-491d-9953-bbae5d936b81","type":"run","title":"Phi-3.5-mini-instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on phi3.5:3.8b-mini-instruct-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 0/3 · tool-flight not supported · needle-8k 2/3 · 103.3 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"fe84e69a-a7ef-4748-8341-e754558f3795","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-19T07:57:28.349Z"}],"updated_at":"2026-10-19T07:57:28.349Z","date":"2026-10-19","visibility":"public"},{"id":"809cb544-af09-411a-830b-23e6dc97651d","type":"run","title":"Qwen3-30B-A3B-Instruct-2507 on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for qwen3:30b-a3b-instruct-2507-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 187.2 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"293deebb-c58e-4abe-a69d-4c3b6be88d7d","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-10T15:41:56.366Z"}],"updated_at":"2026-10-10T15:41:56.366Z","date":"2026-10-10","visibility":"public"},{"id":"68fc3ea3-5593-4593-a2f1-b09f9d294d0c","type":"run","title":"gemma-3-12b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gemma3:12b-it-q4_K_M, NVIDIA GeForce RTX 4070 Ti SUPER · 16 GB.","outcome":"code-intervals 2/3 · tool-flight not supported · needle-8k 3/3 · 62.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"1fa26a95-931d-4cf1-bfd2-da441d80b908","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-09T02:52:31.036Z"}],"updated_at":"2026-10-09T02:52:31.036Z","date":"2026-10-09","visibility":"public"},{"id":"fd1d60e8-d171-45a0-a1f7-14a3a06fdf18","type":"suite","title":"invoice-fields","role":null,"personal_contribution":null,"outcome":"Suite designed for a document-AI startup's launch.","limitations":null,"version":"1.0","links":[],"disclosure":"paid_collaboration","pinned":false,"run_id":null,"evidence":[{"type":"delivery_accepted","label":"Delivery accepted","scope":"The client accepted the delivery against the agreed brief.","does_not_establish":"Does not establish audience reach.","review_status":"passed","version":"1.0","date":"2026-10-04T06:05:30.284Z"}],"updated_at":"2026-10-04T06:05:30.284Z","date":"2026-10-04","visibility":"public"},{"id":"5b48b8f3-e4b7-495f-87f0-0dac7bcfe231","type":"run","title":"Llama-3.1-8B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on llama3.1:8b-instruct-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 1/3 · tool-flight 3/3 · needle-8k 2/3 · 50.2 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"a21f3994-edaa-4aaf-b186-696a1dc2876b","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-02T02:33:17.170Z"}],"updated_at":"2026-10-02T02:33:17.170Z","date":"2026-10-02","visibility":"public"},{"id":"4232bccf-cbfe-44c7-8444-ee7c9dc226a1","type":"article","title":"Why OCR benchmarks lie about receipts","role":null,"personal_contribution":null,"outcome":null,"limitations":null,"version":null,"links":[],"disclosure":"independent","pinned":false,"run_id":null,"evidence":[{"type":"source_linked","label":"Source linked","scope":"The link points to this creator's published work.","does_not_establish":"Does not establish the numbers in it.","review_status":"pending","version":null,"date":"2026-09-27T11:05:30.284Z"}],"updated_at":"2026-09-27T11:05:30.284Z","date":"2026-09-27","visibility":"public"},{"id":"2dc65f70-9261-4169-8189-fafdd0def231","type":"run","title":"gemma-3-4b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gemma3:4b-it-q4_K_M, NVIDIA GeForce RTX 4070 Ti SUPER · 16 GB.","outcome":"code-intervals 2/3 · tool-flight not supported · needle-8k 3/3 · 170.6 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"6ff0fcf7-1785-4d60-9e12-d6c740a7e1b7","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-25T07:34:21.982Z"}],"updated_at":"2026-09-25T07:34:21.982Z","date":"2026-09-25","visibility":"public"},{"id":"335b74ba-dbde-4532-ab9a-8dad68a06c59","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 2/3 · tool-flight 2/3 · needle-8k 3/3 · 49.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"aedc9b08-99a6-445f-961a-b9a3d4ba63ae","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-18T05:14:58.441Z"}],"updated_at":"2026-09-18T05:14:58.441Z","date":"2026-09-18","visibility":"public"},{"id":"2ee5f256-777c-4392-a5a0-5792defd3065","type":"run","title":"MiniCPM5-2B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on openbmb/minicpm5-2b:q4_K_M, NVIDIA GeForce RTX 4070 Ti SUPER · 16 GB.","outcome":"code-intervals 1/3 · tool-flight 1/3 · needle-8k 2/3","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"121661c6-fd4e-4ca8-b29c-89e9dcb70f72","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-11T00:18:18.342Z"}],"updated_at":"2026-09-11T00:18:18.342Z","date":"2026-09-11","visibility":"public"},{"id":"6037e25b-6ee8-4fe5-9a04-3e0f9c5c05ab","type":"run","title":"Phi-3.5-mini-instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on phi3.5:3.8b-mini-instruct-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 1/3 · tool-flight not supported · needle-8k 3/3 · 108.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"759075b0-b2ce-45d0-886b-6a24c5efb605","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-02T17:02:59.704Z"}],"updated_at":"2026-09-02T17:02:59.704Z","date":"2026-09-02","visibility":"public"},{"id":"44600847-2af8-4a4a-bd5c-560a35dddaee","type":"run","title":"Qwen3-4B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:4b-q4_K_M, NVIDIA GeForce RTX 4070 Ti SUPER · 16 GB.","outcome":"code-intervals 1/3 · tool-flight 2/3 · needle-8k 3/3 · 197.7 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"ede94952-f566-49a9-9f89-ee63a7cbb74e","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-08-27T06:11:17.963Z"}],"updated_at":"2026-08-27T06:11:17.963Z","date":"2026-08-27","visibility":"public"},{"id":"ece60248-947c-4ed1-a6ab-0588c806537e","type":"run","title":"Qwen3-14B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:14b-q4_K_M, Apple M3 Max · 64 GB.","outcome":"code-intervals 2/3 · tool-flight 3/3 · needle-8k 3/3 · 27.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"09dd9e39-eb03-4673-9367-e262d0f32b19","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-08-19T11:27:41.938Z"}],"updated_at":"2026-08-19T11:27:41.938Z","date":"2026-08-19","visibility":"public"}],"collaboration":{"formats":["Suite design","Technical review"],"availability":{"slots":1,"month":"December 2026","confirmed_at":"2026-11-02T08:05:30.284Z","unconfirmed":false}},"reputation":{"verified_works":18,"reproductions":1,"tier":"regular"},"updated_at":"2026-11-02T13:05:30.284Z"}