{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KE6WBCWVRYEFHDK7MRH7NMKU37","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":"48dd4289fe0892447bab95f34da7b019d7120993a22cfc9db9ec6fadc8b56910","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T06:38:59Z","title_canon_sha256":"2e0f11cead0c6d280750ae1dec366e4d6fe0f71cfdbdc7f92fb75e919366e6db"},"schema_version":"1.0","source":{"id":"2406.04673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04673","created_at":"2026-07-05T08:28:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04673v1","created_at":"2026-07-05T08:28:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04673","created_at":"2026-07-05T08:28:47Z"},{"alias_kind":"pith_short_12","alias_value":"KE6WBCWVRYEF","created_at":"2026-07-05T08:28:47Z"},{"alias_kind":"pith_short_16","alias_value":"KE6WBCWVRYEFHDK7","created_at":"2026-07-05T08:28:47Z"},{"alias_kind":"pith_short_8","alias_value":"KE6WBCWV","created_at":"2026-07-05T08:28:47Z"}],"graph_snapshots":[{"event_id":"sha256:066374f02103042081ecf53833dcc4630cbdfc8a47f38e35e0f2c5eb2fcea5c4","target":"graph","created_at":"2026-07-05T08:28:47Z","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/2406.04673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music is a universal language that can communicate emotions and feelings. It forms an essential part of the whole spectrum of creative media, ranging from movies to social media posts. Machine learning models that can synthesize music are predominantly conditioned on textual descriptions of it. Inspired by how musicians compose music not just from a movie script, but also through visualizations, we propose MeLFusion, a model that can effectively use cues from a textual description and the corresponding image to synthesize music. MeLFusion is a text-to-music diffusion model with a novel \"visual","authors_text":"Balaji Vasan Srinivasan, Dinesh Manocha, K J Joseph, Sanjoy Chowdhury, Sayan Nag","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T06:38:59Z","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04673","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":"sha256:4a3b1066ae06ec3044efe3f152b436b8543ccfed2ba770637222a1776166b34f","target":"record","created_at":"2026-07-05T08:28:47Z","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":"48dd4289fe0892447bab95f34da7b019d7120993a22cfc9db9ec6fadc8b56910","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T06:38:59Z","title_canon_sha256":"2e0f11cead0c6d280750ae1dec366e4d6fe0f71cfdbdc7f92fb75e919366e6db"},"schema_version":"1.0","source":{"id":"2406.04673","kind":"arxiv","version":1}},"canonical_sha256":"513d608ad58e08538d5f644ff6b154dfef84b6152ce20a012915555f0c5c9776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"513d608ad58e08538d5f644ff6b154dfef84b6152ce20a012915555f0c5c9776","first_computed_at":"2026-07-05T08:28:47.427211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:47.427211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8PBfNc+ha3wffns6VJm+TgMyJSbJGMrwCX/Nc8IvgUGV4dnr8cY3WU2SwmYujRx3UnStqbke1Tx4UfwmZZOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:47.427627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a3b1066ae06ec3044efe3f152b436b8543ccfed2ba770637222a1776166b34f","sha256:066374f02103042081ecf53833dcc4630cbdfc8a47f38e35e0f2c5eb2fcea5c4"],"state_sha256":"0ff110bdb93839a8df27a1e7152f65afee6c464590154614f029b91088a6652f"}