{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q5BW4IRD4MP7EHQB625RY5IBBR","short_pith_number":"pith:Q5BW4IRD","schema_version":"1.0","canonical_sha256":"87436e2223e31ff21e01f6bb1c75010c79a301ef0a8778126feb826139b1b1cf","source":{"kind":"arxiv","id":"2008.06042","version":2},"attestation_state":"computed","paper":{"title":"Image Processing Tools for Financial Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Bairui Du, Delmiro Fernandez-Reyes, Paolo Barucca","submitted_at":"2020-08-13T17:56:17Z","abstract_excerpt":"The application of deep learning to time series forecasting is one of the major challenges in present machine learning. We propose a novel methodology that combines machine learning and image processing methods to define and predict market states with intraday financial data. A wavelet transform is applied to the log-return of stock prices for both image extraction and denoising. A convolutional neural network then extracts patterns from denoised wavelet images to classify daily time series, i.e. a market state is associated with the binary prediction of the daily close price movement based on"},"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":false},"canonical_record":{"source":{"id":"2008.06042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2020-08-13T17:56:17Z","cross_cats_sorted":[],"title_canon_sha256":"c03f949ab365eeddc8c1d9bd1b0d7be54d39492591fa9b328ec98ae40e27fc97","abstract_canon_sha256":"1ea79b8460eb73d5ac5fef67b8ad5b4e18527e4cec0008521bda9c76fcac9087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:49.268325Z","signature_b64":"ERU6UEByQ6NLOPwvfk3bYdH2hveQSyCn0L9TXGsaOAISUJJqeVtIiOIhzsTI0ZypBnBWjkgDjV/EExGGLGGrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87436e2223e31ff21e01f6bb1c75010c79a301ef0a8778126feb826139b1b1cf","last_reissued_at":"2026-07-05T01:27:49.267950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:49.267950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Processing Tools for Financial Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Bairui Du, Delmiro Fernandez-Reyes, Paolo Barucca","submitted_at":"2020-08-13T17:56:17Z","abstract_excerpt":"The application of deep learning to time series forecasting is one of the major challenges in present machine learning. We propose a novel methodology that combines machine learning and image processing methods to define and predict market states with intraday financial data. A wavelet transform is applied to the log-return of stock prices for both image extraction and denoising. A convolutional neural network then extracts patterns from denoised wavelet images to classify daily time series, i.e. a market state is associated with the binary prediction of the daily close price movement based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06042","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.06042/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2008.06042","created_at":"2026-07-05T01:27:49.268010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06042v2","created_at":"2026-07-05T01:27:49.268010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06042","created_at":"2026-07-05T01:27:49.268010+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5BW4IRD4MP7","created_at":"2026-07-05T01:27:49.268010+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5BW4IRD4MP7EHQB","created_at":"2026-07-05T01:27:49.268010+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5BW4IRD","created_at":"2026-07-05T01:27:49.268010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08869","citing_title":"Harnessing Vision Models for Time Series Analysis: A Survey","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR","json":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR.json","graph_json":"https://pith.science/api/pith-number/Q5BW4IRD4MP7EHQB625RY5IBBR/graph.json","events_json":"https://pith.science/api/pith-number/Q5BW4IRD4MP7EHQB625RY5IBBR/events.json","paper":"https://pith.science/paper/Q5BW4IRD"},"agent_actions":{"view_html":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR","download_json":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR.json","view_paper":"https://pith.science/paper/Q5BW4IRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06042&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5BW4IRD4MP7EHQB625RY5IBBR/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5BW4IRD4MP7EHQB625RY5IBBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR/action/storage_attestation","attest_author":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR/action/author_attestation","sign_citation":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR/action/citation_signature","submit_replication":"https://pith.science/pith/Q5BW4IRD4MP7EHQB625RY5IBBR/action/replication_record"}},"created_at":"2026-07-05T01:27:49.268010+00:00","updated_at":"2026-07-05T01:27:49.268010+00:00"}