Date fruit detection dataset for automatic harvesting.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38161658", "kind": "science-record", "revision": 3, "content_hash": "sha256:69475685193cba3a4632c284cb101d4eadd022a0842bdcfcf57d8bbd1006f941", "created_at": "2026-11-01T19:20:05Z", "updated_at": "2026-11-01T22:10:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Date fruit detection dataset for automatic harvesting.", "doi": "10.1016/j.dib.2023.109876", "pmid": "38161658", "authors": ["Yousra Zarouit", "Hassan Zekkouri", "Mohamed Ouhda", "Brahim Aksasse"], "journal": "Data in brief", "year": 2024, "abstract": "Date fruit is one of the most beneficial and delicious fruits in the world through its nutritional value, it's a rich source of sugar, Protein, Manganese, Fibers, and many other vitamins, on the other hand, date production in the world reached up to 9.45 million tons, one palm tree can produce dates for 40-50 years which makes date production one of the main pillars of the economy. Generally, the methods used for pre and post-harvesting are done manually, making the operation heavy in terms of time and economy. Research in the area of harvesting automation is still limited due to the absence of data. This work presents a full dataset for detection, classification, analysis, and harvesting decisions. The dataset contains a collection of images and videos for different varieties of dates at different stages of maturity, taking into consideration all the natural conditions including light, contrast, dates in bags, and multi-scaled images. The big advantage of this dataset is it can help to put agriculture research at an advanced level by robotizing all the pre and post-harvesting tasks. The dataset is published for free in ZENODO [1] https://zenodo.org/doi/10.5281/zenodo.8315234.", "claims": [{"id": "claim-data-access", "statement": "Date Fruit Detection Dataset for Computer Vision-Based Automatic Harvesting (Original data) (ZENODO)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38161658", "locator": "sections[9] \"Data Availability\" paragraph 2", "quote": "Date Fruit Detection Dataset for Computer Vision-Based Automatic Harvesting (Original data) (ZENODO)"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:38161658"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38161658", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2023.109876", "sha256": "sha256:c6e08d1a07bf038d76808cb9d4c40985d19fb98beb1edd5322ece03fe66e52fd", "bytes": 16351, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2023.109876", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10754698", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "image_quantification", "specific": "segmentation", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "object detection"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: segmentation."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Date Fruit Detection Dataset for Computer Vision-Based Automatic Harvesting (Original data) (ZENODO)"], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["segment_objects", "quantify_intensity"], "assets": ["source:pmid:38161658"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:03:49Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5175, "completion_tokens": 1057, "cached_tokens": 128}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38161658", "type": "paper", "label": "pmid:38161658"}, {"id": "source:pmid:38161658", "type": "manuscript", "label": "PMID 38161658 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38161658", "type": "paper", "label": "pmid:38161658"}, {"id": "source:pmid:38161658", "type": "manuscript", "label": "PMID 38161658 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38161658", "type": "extraction", "used": ["source:pmid:38161658"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:38161658", "parent_hash": "sha256:4f0afb8a7c5b83cc759d1721347a71cb111de6cd81f2798b57151fc24dd73d7c", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "image_quantification", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["segment_objects", "quantify_intensity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["object detection"], "order_basis": "analysis_only", "id": "assay:1"}]}