{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IZIVNDYAELY745QWYG2BBDVHWW","short_pith_number":"pith:IZIVNDYA","canonical_record":{"source":{"id":"1704.06761","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-04-22T07:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"87907056e6d2a729cb95954ec91e69834e308f8050f426cb77a6351b790c07af","abstract_canon_sha256":"431dbfaa34ee664a8d236cd587614cce3ed1cd05eda6e50380e1ea2fac4981d6"},"schema_version":"1.0"},"canonical_sha256":"4651568f0022f1fe7616c1b4108ea7b5b171ee759780fa1c659b720d26409536","source":{"kind":"arxiv","id":"1704.06761","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06761","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06761v2","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06761","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"pith_short_12","alias_value":"IZIVNDYAELY7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IZIVNDYAELY745QW","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IZIVNDYA","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IZIVNDYAELY745QWYG2BBDVHWW","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06761","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-04-22T07:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"87907056e6d2a729cb95954ec91e69834e308f8050f426cb77a6351b790c07af","abstract_canon_sha256":"431dbfaa34ee664a8d236cd587614cce3ed1cd05eda6e50380e1ea2fac4981d6"},"schema_version":"1.0"},"canonical_sha256":"4651568f0022f1fe7616c1b4108ea7b5b171ee759780fa1c659b720d26409536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:14.077346Z","signature_b64":"NOV2QnR6zLbMdmpVyW+BCq8NcSlWh5oi4tyCj99SnhXH7UVf1pige9ieUHDr7MQ4d4VzQfwFFHGnnXwOBoP5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4651568f0022f1fe7616c1b4108ea7b5b171ee759780fa1c659b720d26409536","last_reissued_at":"2026-05-18T00:36:14.076638Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:14.076638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06761","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lgCK9Kn16TGJ8v5QonxELKPKjQa61rrXFvDI9DZbPVDcSmSFM3sqjD+MQDLMjLKXeNEZcgIscIRcNqZfhFYvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:25:32.945253Z"},"content_sha256":"03153b3b43668e5b7efa046ad936706deeb2f4707d4b97b80700f012173de609","schema_version":"1.0","event_id":"sha256:03153b3b43668e5b7efa046ad936706deeb2f4707d4b97b80700f012173de609"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IZIVNDYAELY745QWYG2BBDVHWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyun S. Yang, Sungeun Hong, Woobin Im","submitted_at":"2017-04-22T07:40:16Z","abstract_excerpt":"Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa. Moreover, much of the existing research relies on metadata such as keywords, tags, or associated description that must be individually produced and attached posterior. This paper introduces a new content-based, cross-modal retrieval method for video and music that is implemented through deep neural networks. We train the network via inter-modal ranking loss such that videos and music with similar semantics end up close together in the embedding space. However, if "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06761","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":""},"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":"2026-05-18T00:36:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEY9OSjH4smDXr6nMTcIx9SWdId8x6DvlklK1PMVl0UJBSMJ6FzuQAbxle7Tjl7LgsbPfQCZ/VxZbuhWaHxpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:25:32.945997Z"},"content_sha256":"035a8e74c471700e4a799108543463c0463e10ff45ad87e416fdb91c32672b6d","schema_version":"1.0","event_id":"sha256:035a8e74c471700e4a799108543463c0463e10ff45ad87e416fdb91c32672b6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZIVNDYAELY745QWYG2BBDVHWW/bundle.json","state_url":"https://pith.science/pith/IZIVNDYAELY745QWYG2BBDVHWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZIVNDYAELY745QWYG2BBDVHWW/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":"2026-06-10T05:25:32Z","links":{"resolver":"https://pith.science/pith/IZIVNDYAELY745QWYG2BBDVHWW","bundle":"https://pith.science/pith/IZIVNDYAELY745QWYG2BBDVHWW/bundle.json","state":"https://pith.science/pith/IZIVNDYAELY745QWYG2BBDVHWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZIVNDYAELY745QWYG2BBDVHWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IZIVNDYAELY745QWYG2BBDVHWW","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":"431dbfaa34ee664a8d236cd587614cce3ed1cd05eda6e50380e1ea2fac4981d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-04-22T07:40:16Z","title_canon_sha256":"87907056e6d2a729cb95954ec91e69834e308f8050f426cb77a6351b790c07af"},"schema_version":"1.0","source":{"id":"1704.06761","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06761","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06761v2","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06761","created_at":"2026-05-18T00:36:14Z"},{"alias_kind":"pith_short_12","alias_value":"IZIVNDYAELY7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IZIVNDYAELY745QW","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IZIVNDYA","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:035a8e74c471700e4a799108543463c0463e10ff45ad87e416fdb91c32672b6d","target":"graph","created_at":"2026-05-18T00:36:14Z","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"},"paper":{"abstract_excerpt":"Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa. Moreover, much of the existing research relies on metadata such as keywords, tags, or associated description that must be individually produced and attached posterior. This paper introduces a new content-based, cross-modal retrieval method for video and music that is implemented through deep neural networks. We train the network via inter-modal ranking loss such that videos and music with similar semantics end up close together in the embedding space. However, if ","authors_text":"Hyun S. Yang, Sungeun Hong, Woobin Im","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-04-22T07:40:16Z","title":"Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06761","kind":"arxiv","version":2},"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":"sha256:03153b3b43668e5b7efa046ad936706deeb2f4707d4b97b80700f012173de609","target":"record","created_at":"2026-05-18T00:36:14Z","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":"431dbfaa34ee664a8d236cd587614cce3ed1cd05eda6e50380e1ea2fac4981d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-04-22T07:40:16Z","title_canon_sha256":"87907056e6d2a729cb95954ec91e69834e308f8050f426cb77a6351b790c07af"},"schema_version":"1.0","source":{"id":"1704.06761","kind":"arxiv","version":2}},"canonical_sha256":"4651568f0022f1fe7616c1b4108ea7b5b171ee759780fa1c659b720d26409536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4651568f0022f1fe7616c1b4108ea7b5b171ee759780fa1c659b720d26409536","first_computed_at":"2026-05-18T00:36:14.076638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:14.076638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NOV2QnR6zLbMdmpVyW+BCq8NcSlWh5oi4tyCj99SnhXH7UVf1pige9ieUHDr7MQ4d4VzQfwFFHGnnXwOBoP5Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:14.077346Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06761","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03153b3b43668e5b7efa046ad936706deeb2f4707d4b97b80700f012173de609","sha256:035a8e74c471700e4a799108543463c0463e10ff45ad87e416fdb91c32672b6d"],"state_sha256":"4a6f871fbbe0a48fdc3142b5487b482ca70de1df657571137eee3f3d29c5de10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZ347cRLGVDNjr1VwD5q4Yz+jql27CTiE41MxiC/PXwU0BhrK/ZflJxfyc67on0w4/R1ScWxfgecfNcMI6WXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T05:25:32.949607Z","bundle_sha256":"fa3022ca82c6a4f795a798300c80d8a3c4ef60f6802bc731cc66344ce3783233"}}