{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WRKWD2RUBILCZGRSEDK3VKODY3","short_pith_number":"pith:WRKWD2RU","schema_version":"1.0","canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","source":{"kind":"arxiv","id":"2509.05786","version":1},"attestation_state":"computed","paper":{"title":"Effectively obtaining acoustic, visual and textual data from videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Jorge E. Le\\'on, Miguel Carrasco","submitted_at":"2025-09-06T17:42:22Z","abstract_excerpt":"The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains limited. This paper addresses this gap by proposing a method to extract related audio-image-text observations from videos. We detail the process of selecting suitable videos, extracting relevant data pairs, and generating descriptive texts using image-to-text models. Our approach ensures a robust semantic connection between modalities, enhancing the utility of t"},"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":"2509.05786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-09-06T17:42:22Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2987c3f59ef527cef8f3469607040e9a448a6e5af08648b209ed4d52f1a8bdda","abstract_canon_sha256":"bf5290a6a1b3596408971137628970ff86053a8d9d4866f6b35199300939146f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:24.205178Z","signature_b64":"K3wUvoBW59fo7C2wuXM+8vMJaygYEyo22x5tF/+fBosbVuqc2YzNp5vVT6dNYwv0N1NAjhhabbyu101qDgnrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","last_reissued_at":"2026-07-05T12:06:24.204559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:24.204559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effectively obtaining acoustic, visual and textual data from videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Jorge E. Le\\'on, Miguel Carrasco","submitted_at":"2025-09-06T17:42:22Z","abstract_excerpt":"The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains limited. This paper addresses this gap by proposing a method to extract related audio-image-text observations from videos. We detail the process of selecting suitable videos, extracting relevant data pairs, and generating descriptive texts using image-to-text models. Our approach ensures a robust semantic connection between modalities, enhancing the utility of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05786","kind":"arxiv","version":1},"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/2509.05786/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":"2509.05786","created_at":"2026-07-05T12:06:24.204610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05786v1","created_at":"2026-07-05T12:06:24.204610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05786","created_at":"2026-07-05T12:06:24.204610+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRKWD2RUBILC","created_at":"2026-07-05T12:06:24.204610+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRKWD2RUBILCZGRS","created_at":"2026-07-05T12:06:24.204610+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRKWD2RU","created_at":"2026-07-05T12:06:24.204610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.09717","citing_title":"Testing chatbots on the creation of encoders for audio conditioned image generation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3","json":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3.json","graph_json":"https://pith.science/api/pith-number/WRKWD2RUBILCZGRSEDK3VKODY3/graph.json","events_json":"https://pith.science/api/pith-number/WRKWD2RUBILCZGRSEDK3VKODY3/events.json","paper":"https://pith.science/paper/WRKWD2RU"},"agent_actions":{"view_html":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3","download_json":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3.json","view_paper":"https://pith.science/paper/WRKWD2RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05786&json=true","fetch_graph":"https://pith.science/api/pith-number/WRKWD2RUBILCZGRSEDK3VKODY3/graph.json","fetch_events":"https://pith.science/api/pith-number/WRKWD2RUBILCZGRSEDK3VKODY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/action/storage_attestation","attest_author":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/action/author_attestation","sign_citation":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/action/citation_signature","submit_replication":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/action/replication_record"}},"created_at":"2026-07-05T12:06:24.204610+00:00","updated_at":"2026-07-05T12:06:24.204610+00:00"}