{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B74HQEQC5MJMLIJCZUNQTOLGUZ","short_pith_number":"pith:B74HQEQC","schema_version":"1.0","canonical_sha256":"0ff8781202eb12c5a122cd1b09b966a661709234b2c46326f6ca8bd53dca877e","source":{"kind":"arxiv","id":"2601.15769","version":3},"attestation_state":"computed","paper":{"title":"Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Polarization eigen-parameters from holographic microscopy let a neural network classify microplastic fibers at 96.7 percent accuracy.","cross_cats":["physics.data-an"],"primary_cat":"physics.optics","authors_text":"Giulia Dalla Fontana, Jan Appel, Jarom\\'ir B\\v{e}hal, Lisa Miccio, Marika Valentino, Miroslav Je\\v{z}ek, Pietro Ferraro, Raffaella Mossotti, Vittorio Bianco","submitted_at":"2026-01-22T08:59:55Z","abstract_excerpt":"Reliable identification of microplastic fibers is crucial for environmental monitoring but remains analytically challenging. We report an explainable deep-learning framework for classifying microplastic and natural microfibers using polarization-resolved digital holographic microscopy. From multiplexed holograms, the complex Jones matrix of each fiber was reconstructed to extract polarization eigen-parameters describing optical anisotropy. Statistical descriptors of nine polarization characteristics formed a 72-dimensional feature vector for a total of 296 fibers spanning six material classes,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2601.15769","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.optics","submitted_at":"2026-01-22T08:59:55Z","cross_cats_sorted":["physics.data-an"],"title_canon_sha256":"e0b60406c32622496a568cf209c7eed3fb55d28b3c6590cbb2fa47c6385361ea","abstract_canon_sha256":"1dce4e206ffdd62af86700f404a7b45b32d78b5fe151002db0318ae868ef93e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:29.753326Z","signature_b64":"T9haDolptiL9QbVWCqjqt4w7QCpxPnJ6jZVmorFaLX0s0E17u8aSwTyhU9q1CcNNZ7t/zwPsQZxZuxEbDic0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ff8781202eb12c5a122cd1b09b966a661709234b2c46326f6ca8bd53dca877e","last_reissued_at":"2026-06-01T01:02:29.752422Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:29.752422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Polarization eigen-parameters from holographic microscopy let a neural network classify microplastic fibers at 96.7 percent accuracy.","cross_cats":["physics.data-an"],"primary_cat":"physics.optics","authors_text":"Giulia Dalla Fontana, Jan Appel, Jarom\\'ir B\\v{e}hal, Lisa Miccio, Marika Valentino, Miroslav Je\\v{z}ek, Pietro Ferraro, Raffaella Mossotti, Vittorio Bianco","submitted_at":"2026-01-22T08:59:55Z","abstract_excerpt":"Reliable identification of microplastic fibers is crucial for environmental monitoring but remains analytically challenging. We report an explainable deep-learning framework for classifying microplastic and natural microfibers using polarization-resolved digital holographic microscopy. From multiplexed holograms, the complex Jones matrix of each fiber was reconstructed to extract polarization eigen-parameters describing optical anisotropy. Statistical descriptors of nine polarization characteristics formed a 72-dimensional feature vector for a total of 296 fibers spanning six material classes,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The designed fully connected deep neural network achieved an accuracy of 96.7 % on the validation data, surpassing that of common machine-learning classifiers. An additional reduced-feature model with the preserved architecture exploiting only these most significant eigenvalue-based characteristics retained high accuracy (93.3 %).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 296 laboratory-prepared fibers and their extracted polarization descriptors are representative of the diversity, degradation states, and confounding factors (size, orientation, surface contamination) encountered in real environmental samples.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A deep neural network classifies six types of microplastic and natural fibers using 72-dimensional polarization feature vectors from holographic microscopy at 96.7% accuracy, with SHAP analysis showing eigenvalue ratios as the dominant predictors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Polarization eigen-parameters from holographic microscopy let a neural network classify microplastic fibers at 96.7 percent accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"85853c2bd6945ff5cc794fd59df803f3f535fc09b01d6bb1d348926e06a74f4c"},"source":{"id":"2601.15769","kind":"arxiv","version":3},"verdict":{"id":"6904f2fc-5896-477e-84dd-081eaf990b58","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T12:22:24.779302Z","strongest_claim":"The designed fully connected deep neural network achieved an accuracy of 96.7 % on the validation data, surpassing that of common machine-learning classifiers. An additional reduced-feature model with the preserved architecture exploiting only these most significant eigenvalue-based characteristics retained high accuracy (93.3 %).","one_line_summary":"A deep neural network classifies six types of microplastic and natural fibers using 72-dimensional polarization feature vectors from holographic microscopy at 96.7% accuracy, with SHAP analysis showing eigenvalue ratios as the dominant predictors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 296 laboratory-prepared fibers and their extracted polarization descriptors are representative of the diversity, degradation states, and confounding factors (size, orientation, surface contamination) encountered in real environmental samples.","pith_extraction_headline":"Polarization eigen-parameters from holographic microscopy let a neural network classify microplastic fibers at 96.7 percent accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.15769/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7829de7fac9441bd4889234703c185fba2a8684615583111482ff846cc67c9ac"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.15769","created_at":"2026-06-01T01:02:29.752597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15769v3","created_at":"2026-06-01T01:02:29.752597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15769","created_at":"2026-06-01T01:02:29.752597+00:00"},{"alias_kind":"pith_short_12","alias_value":"B74HQEQC5MJM","created_at":"2026-06-01T01:02:29.752597+00:00"},{"alias_kind":"pith_short_16","alias_value":"B74HQEQC5MJMLIJC","created_at":"2026-06-01T01:02:29.752597+00:00"},{"alias_kind":"pith_short_8","alias_value":"B74HQEQC","created_at":"2026-06-01T01:02:29.752597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ","json":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ.json","graph_json":"https://pith.science/api/pith-number/B74HQEQC5MJMLIJCZUNQTOLGUZ/graph.json","events_json":"https://pith.science/api/pith-number/B74HQEQC5MJMLIJCZUNQTOLGUZ/events.json","paper":"https://pith.science/paper/B74HQEQC"},"agent_actions":{"view_html":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ","download_json":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ.json","view_paper":"https://pith.science/paper/B74HQEQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15769&json=true","fetch_graph":"https://pith.science/api/pith-number/B74HQEQC5MJMLIJCZUNQTOLGUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/B74HQEQC5MJMLIJCZUNQTOLGUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ/action/storage_attestation","attest_author":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ/action/author_attestation","sign_citation":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ/action/citation_signature","submit_replication":"https://pith.science/pith/B74HQEQC5MJMLIJCZUNQTOLGUZ/action/replication_record"}},"created_at":"2026-06-01T01:02:29.752597+00:00","updated_at":"2026-06-01T01:02:29.752597+00:00"}