{"schema":"record/v1","id":"src_01M65HJJA2CN6DAK5EGZZHJMGF","type":"source","revision":1,"etag":"\"r1.s0\"","title":"SoyVitou/KhmerSynthetic1M","summary":"Hugging Face dataset SoyVitou/KhmerSynthetic1M at revision ca57f6ac4442: modalities image, text; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","status":"active","body":{"text":"created at: 2026-01-31T18:08:59.000Z\nformats: [\"parquet\"]\ngated: false\nlast modified: 2026-02-01T10:52:31.000Z\nlicense: apache-2.0\nmodalities: [\"image\", \"text\"]\nsize categories: [\"1M<n<10M\"]","archived":null,"revision":{"ref":"ca57f6ac4442d16d0ead3bc6d423f0375990a2ce","pinned":true,"source_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M/tree/ca57f6ac4442d16d0ead3bc6d423f0375990a2ce"},"checked_at":"2026-10-29T01:16:41.000Z","parent_url":null,"usefulness":"Locate SoyVitou/KhmerSynthetic1M and check its declared licence, access and lineage before use.","source_type":"dataset","availability":"available","dependencies":[],"source_owner":"SoyVitou","canonical_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M","next_check_at":null,"successor_url":null,"hardware_notes":null,"known_limitations":["Metadata-only index entry from the Hugging Face listing observed 2026-10-29.","Not fetched or reviewed: card text, files, weights, licence text and linked media; nothing was run.","Declared values come from the uploader or listing and may change after the pinned revision."],"upstream_updated_at":"2026-02-01T10:52:31.000Z"},"categories":["T05"],"tags":["metadata-index"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[],"execution_record_ids":[]},"rights":[{"notes":"Original attributed summary of public listing fields (identifiers, pins and declared values) only. The upstream repository, its card, files, weights and media remain governed by their own terms.","hosting":"permitted","component":"documentation","license_id":null,"modification":"permitted","evidence_urls":[],"model_training":"unknown","redistribution":"permitted"}],"attribution":{"origin":"research_agent","upstream_owner":null,"upstream_url":null,"imported_from":"records/p-46ec0dd95cfd0eeb2f4eee517cb77d078e615ab2/record.json#p-46ec0dd95cfd0eeb2f4eee517cb77d078e615ab2/record","import_batch_id":"pipe-c60cc29209dc10ee33f9319f5702b45c767e47fc","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"pipe-c60cc29209dc10ee33f9319f5702b45c767e47fc","original":{"body":{"text":"created at: 2026-01-31T18:08:59.000Z\nformats: [\"parquet\"]\ngated: false\nlast modified: 2026-02-01T10:52:31.000Z\nlicense: apache-2.0\nmodalities: [\"image\", \"text\"]\nsize categories: [\"1M<n<10M\"]","revision":{"ref":"ca57f6ac4442d16d0ead3bc6d423f0375990a2ce","pinned":true,"source_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M/tree/ca57f6ac4442d16d0ead3bc6d423f0375990a2ce"},"checked_at":"2026-10-29T01:16:41.000Z","usefulness":"Locate SoyVitou/KhmerSynthetic1M and check its declared licence, access and lineage before use.","source_type":"dataset","availability":"available","source_owner":"SoyVitou","canonical_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M","known_limitations":["Metadata-only index entry from the Hugging Face listing observed 2026-10-29.","Not fetched or reviewed: card text, files, weights, licence text and linked media; nothing was run.","Declared values come from the uploader or listing and may change after the pinned revision."],"upstream_updated_at":"2026-02-01T10:52:31.000Z"},"tags":["metadata-index"],"type":"source","title":"SoyVitou/KhmerSynthetic1M","rights":[{"notes":"Original attributed summary of public listing fields (identifiers, pins and declared values) only. The upstream repository, its card, files, weights and media remain governed by their own terms.","hosting":"permitted","component":"documentation","license_id":null,"modification":"permitted","evidence_urls":[],"model_training":"unknown","redistribution":"permitted"}],"summary":"Hugging Face dataset SoyVitou/KhmerSynthetic1M at revision ca57f6ac4442: modalities image, text; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","evidence":{"review":"unreviewed","execution":"not_run","inspection":"metadata_checked"},"language":"en","categories":["T05"],"extensions":{"curation/v1":{"curator":"windows-claude-scale67-bulk","revision":1,"topic_ids":[],"confidence":"Deterministic projection of the pinned listing row; the frontier curator approved the batch mapping, fields and exclusions. Card, files and terms were not reviewed.","limitations":["Metadata-only index entry from the Hugging Face listing observed 2026-10-29.","Not fetched or reviewed: card text, files, weights, licence text and linked media; nothing was run.","Declared values come from the uploader or listing and may change after the pinned revision."],"observed_at":"2026-10-29T01:16:41.000Z","source_pins":[{"locator":"INVENTORY.json; asset SoyVitou/KhmerSynthetic1M","source_id":"WIN-S-766e18a0c9edbf00ec2dd83410693c06","version_id":"WIN-V-d37c8f6e762a7011bda770b293633e67","observed_at":"2026-10-29T01:16:41.000Z","canonical_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M","version_sha256":"10fa04934593f1c35c88f6e87011b0e6f81bd0abeeab3bcd41b3b518f7426b0f"}],"candidate_id":"WIN-K-5385860d6e97cd591514817fd8579710948ac650","claim_status":"source_fact","rights_basis":"Original summary of listing fields; no card text, files or media redistributed.","qualification":"shared_operator_desk_qa","supersedes_sha256":null}},"visibility":"public"},"observed_on":null,"original_id":"p-46ec0dd95cfd0eeb2f4eee517cb77d078e615ab2/record","source_file":"records/p-46ec0dd95cfd0eeb2f4eee517cb77d078e615ab2/record.json","research_side":{},"source_schema":"create-record-input/v1","original_sha256":"bfd6f1602fea6eba2b033ae07efb032c935ea8d0f23a82a6d8b4f23025444f5e","unmapped_fields":[]}],"publication":{"rule":"item_visibility","policy":"l05-publication/1","visibility":"public"}},"curation/v1":{"curator":"windows-claude-scale67-bulk","revision":1,"topic_ids":[],"confidence":"Deterministic projection of the pinned listing row; the frontier curator approved the batch mapping, fields and exclusions. Card, files and terms were not reviewed.","limitations":["Metadata-only index entry from the Hugging Face listing observed 2026-10-29.","Not fetched or reviewed: card text, files, weights, licence text and linked media; nothing was run.","Declared values come from the uploader or listing and may change after the pinned revision."],"observed_at":"2026-10-29T01:16:41.000Z","source_pins":[{"locator":"INVENTORY.json; asset SoyVitou/KhmerSynthetic1M","source_id":"WIN-S-766e18a0c9edbf00ec2dd83410693c06","version_id":"WIN-V-d37c8f6e762a7011bda770b293633e67","observed_at":"2026-10-29T01:16:41.000Z","canonical_url":"https://huggingface.co/datasets/SoyVitou/KhmerSynthetic1M","version_sha256":"10fa04934593f1c35c88f6e87011b0e6f81bd0abeeab3bcd41b3b518f7426b0f"}],"candidate_id":"WIN-K-5385860d6e97cd591514817fd8579710948ac650","claim_status":"source_fact","rights_basis":"Original summary of listing fields; no card text, files or media redistributed.","qualification":"shared_operator_desk_qa","supersedes_sha256":null}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M65HJJA2CN6DAK5EGZZHJMGF","api_url":"https://veyrul.com/v1/records/src_01M65HJJA2CN6DAK5EGZZHJMGF","created_at":"2026-10-30T04:37:32.570Z","updated_at":"2026-10-30T04:37:32.570Z","last_activity_at":"2026-10-30T04:37:32.570Z"}