{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DF2FM75W2MPORUUOC2BUW4PMEO","short_pith_number":"pith:DF2FM75W","schema_version":"1.0","canonical_sha256":"1974567fb6d31ee8d28e16834b71ec238bdf8c3fd2777db8285a6b6ffa1cfd44","source":{"kind":"arxiv","id":"2308.12610","version":3},"attestation_state":"computed","paper":{"title":"Emotion-Aligned Contrastive Learning Between Images and Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Kleanthis Avramidis, Shanti Stewart, Shrikanth Narayanan, Tiantian Feng","submitted_at":"2023-08-24T07:20:47Z","abstract_excerpt":"Traditional music search engines rely on retrieval methods that match natural language queries with music metadata. There have been increasing efforts to expand retrieval methods to consider the audio characteristics of music itself, using queries of various modalities including text, video, and speech. While most approaches aim to match general music semantics to the input queries, only a few focus on affective qualities. In this work, we address the task of retrieving emotionally-relevant music from image queries by learning an affective alignment between images and music audio. Our approach"},"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":"2308.12610","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-08-24T07:20:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ce65c4d70de038cfe438962a275b6503f4642bff95afad4f1d993c1fb26f87ce","abstract_canon_sha256":"a0efddf51f25bd112e85dc2b88ddae56a19760989b65784a0d86ac97479e6d5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:41.071983Z","signature_b64":"BU+v/BYBlJnjZEWL/z3LLLZz4Lu/Li9vmL91xBv+6F6Z7arv+b/m0BRTmXi9XU4bC1bZ+OJU+7uSlqNKPezGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1974567fb6d31ee8d28e16834b71ec238bdf8c3fd2777db8285a6b6ffa1cfd44","last_reissued_at":"2026-07-05T09:45:41.071573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:41.071573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion-Aligned Contrastive Learning Between Images and Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Kleanthis Avramidis, Shanti Stewart, Shrikanth Narayanan, Tiantian Feng","submitted_at":"2023-08-24T07:20:47Z","abstract_excerpt":"Traditional music search engines rely on retrieval methods that match natural language queries with music metadata. There have been increasing efforts to expand retrieval methods to consider the audio characteristics of music itself, using queries of various modalities including text, video, and speech. While most approaches aim to match general music semantics to the input queries, only a few focus on affective qualities. In this work, we address the task of retrieving emotionally-relevant music from image queries by learning an affective alignment between images and music audio. Our approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12610","kind":"arxiv","version":3},"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/2308.12610/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":"2308.12610","created_at":"2026-07-05T09:45:41.071627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12610v3","created_at":"2026-07-05T09:45:41.071627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12610","created_at":"2026-07-05T09:45:41.071627+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF2FM75W2MPO","created_at":"2026-07-05T09:45:41.071627+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF2FM75W2MPORUUO","created_at":"2026-07-05T09:45:41.071627+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF2FM75W","created_at":"2026-07-05T09:45:41.071627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO","json":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO.json","graph_json":"https://pith.science/api/pith-number/DF2FM75W2MPORUUOC2BUW4PMEO/graph.json","events_json":"https://pith.science/api/pith-number/DF2FM75W2MPORUUOC2BUW4PMEO/events.json","paper":"https://pith.science/paper/DF2FM75W"},"agent_actions":{"view_html":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO","download_json":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO.json","view_paper":"https://pith.science/paper/DF2FM75W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12610&json=true","fetch_graph":"https://pith.science/api/pith-number/DF2FM75W2MPORUUOC2BUW4PMEO/graph.json","fetch_events":"https://pith.science/api/pith-number/DF2FM75W2MPORUUOC2BUW4PMEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO/action/storage_attestation","attest_author":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO/action/author_attestation","sign_citation":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO/action/citation_signature","submit_replication":"https://pith.science/pith/DF2FM75W2MPORUUOC2BUW4PMEO/action/replication_record"}},"created_at":"2026-07-05T09:45:41.071627+00:00","updated_at":"2026-07-05T09:45:41.071627+00:00"}