{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WRKWD2RUBILCZGRSEDK3VKODY3","short_pith_number":"pith:WRKWD2RU","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"},"canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","source":{"kind":"arxiv","id":"2509.05786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05786","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05786v1","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05786","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"WRKWD2RUBILC","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"WRKWD2RUBILCZGRS","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"WRKWD2RU","created_at":"2026-07-05T12:06:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WRKWD2RUBILCZGRSEDK3VKODY3","target":"record","payload":{"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"},"canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","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"},"source_kind":"arxiv","source_id":"2509.05786","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hzEuFIl18bIunhAmQaY3GxK2shZFnW/NnogWaL0t57ZHBepbWbTaXVFEzttYr7i9G78DTcZHKqTG0444vivCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:09:21.253637Z"},"content_sha256":"f398ee748165871763b5c3cc1a25ed24542ef7abc7b8793d17a791639a5c6e8d","schema_version":"1.0","event_id":"sha256:f398ee748165871763b5c3cc1a25ed24542ef7abc7b8793d17a791639a5c6e8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WRKWD2RUBILCZGRSEDK3VKODY3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TKkD5fEUY6rikqz0g3jrWtB/GRtAD779vbRl3rCoDdiC+PGbZoKd9cyZqaAnDXfDJ9IFiIR+AOYOaiCa4p2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:09:21.254120Z"},"content_sha256":"22fa8fc0673187004ee0dd15ab1c736fe42f4c9f3740f8a6166388ee74478e16","schema_version":"1.0","event_id":"sha256:22fa8fc0673187004ee0dd15ab1c736fe42f4c9f3740f8a6166388ee74478e16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/bundle.json","state_url":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRKWD2RUBILCZGRSEDK3VKODY3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:09:21Z","links":{"resolver":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3","bundle":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/bundle.json","state":"https://pith.science/pith/WRKWD2RUBILCZGRSEDK3VKODY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRKWD2RUBILCZGRSEDK3VKODY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WRKWD2RUBILCZGRSEDK3VKODY3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bf5290a6a1b3596408971137628970ff86053a8d9d4866f6b35199300939146f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-09-06T17:42:22Z","title_canon_sha256":"2987c3f59ef527cef8f3469607040e9a448a6e5af08648b209ed4d52f1a8bdda"},"schema_version":"1.0","source":{"id":"2509.05786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05786","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05786v1","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05786","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"WRKWD2RUBILC","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"WRKWD2RUBILCZGRS","created_at":"2026-07-05T12:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"WRKWD2RU","created_at":"2026-07-05T12:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:22fa8fc0673187004ee0dd15ab1c736fe42f4c9f3740f8a6166388ee74478e16","target":"graph","created_at":"2026-07-05T12:06:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.05786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jorge E. Le\\'on, Miguel Carrasco","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05786","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f398ee748165871763b5c3cc1a25ed24542ef7abc7b8793d17a791639a5c6e8d","target":"record","created_at":"2026-07-05T12:06:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bf5290a6a1b3596408971137628970ff86053a8d9d4866f6b35199300939146f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-09-06T17:42:22Z","title_canon_sha256":"2987c3f59ef527cef8f3469607040e9a448a6e5af08648b209ed4d52f1a8bdda"},"schema_version":"1.0","source":{"id":"2509.05786","kind":"arxiv","version":1}},"canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b45561ea340a162c9a3220d5baa9c3c6fac7ad30f9b8867227e81a25f8e79cae","first_computed_at":"2026-07-05T12:06:24.204559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:24.204559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K3wUvoBW59fo7C2wuXM+8vMJaygYEyo22x5tF/+fBosbVuqc2YzNp5vVT6dNYwv0N1NAjhhabbyu101qDgnrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:24.205178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f398ee748165871763b5c3cc1a25ed24542ef7abc7b8793d17a791639a5c6e8d","sha256:22fa8fc0673187004ee0dd15ab1c736fe42f4c9f3740f8a6166388ee74478e16"],"state_sha256":"9233aaad71c4793f33d33723180677cd608f694d051dafb1f743ec36f8224f6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSpYa1P/B59dIuVF8fYaI/XuBvFWL4OL3DH5UrszQZuE85RCE3FUt9CXOzaVjiGKX2aR8z5ko3W8g5BAVm6tDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:09:21.257267Z","bundle_sha256":"5858be5c5014dd714a449cfc479ae9cf75c71c0f9925aa51e07fc7a6ef087dd7"}}