{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6RSYEFYJ5CJA5HYWOYUNNWLJXL","short_pith_number":"pith:6RSYEFYJ","canonical_record":{"source":{"id":"2501.05413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-09T18:13:57Z","cross_cats_sorted":["cs.CV","cs.GR","eess.AS"],"title_canon_sha256":"fc153a50ec68dd2d409ccfa8abcb048105727e4e5cbf7acf22d3dc46d97ddb2b","abstract_canon_sha256":"ec14bd32d60c53fe0d105453c74b516bc368eac2e9b7efa0ae6962336e36d2db"},"schema_version":"1.0"},"canonical_sha256":"f465821709e8920e9f167628d6d969bacf6494f9584a13b55484540d9f47d409","source":{"kind":"arxiv","id":"2501.05413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05413","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05413v1","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05413","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"6RSYEFYJ5CJA","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"6RSYEFYJ5CJA5HYW","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"6RSYEFYJ","created_at":"2026-07-05T09:59:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6RSYEFYJ5CJA5HYWOYUNNWLJXL","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-09T18:13:57Z","cross_cats_sorted":["cs.CV","cs.GR","eess.AS"],"title_canon_sha256":"fc153a50ec68dd2d409ccfa8abcb048105727e4e5cbf7acf22d3dc46d97ddb2b","abstract_canon_sha256":"ec14bd32d60c53fe0d105453c74b516bc368eac2e9b7efa0ae6962336e36d2db"},"schema_version":"1.0"},"canonical_sha256":"f465821709e8920e9f167628d6d969bacf6494f9584a13b55484540d9f47d409","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:09.579837Z","signature_b64":"KvrfGgprOtmNo9Swy5FYcbOGx8kWBKTTDArrQjmOFtgqMeM62chJq+SBZaxcEfBl63YDKac8l8bDgeniAEwkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f465821709e8920e9f167628d6d969bacf6494f9584a13b55484540d9f47d409","last_reissued_at":"2026-07-05T09:59:09.579333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:09.579333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05413","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":"2026-07-05T09:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6//VyqY05zJC/85OTNHNMOX/N6fz5p5JqG3KVpQhqhVwhXkEKAiYrSIk784USHR56Zr5yId0YhyMpuOrQsQoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:48:45.368785Z"},"content_sha256":"88f15b97b0b556bbdceda272f531b9855c671cd970a2c334a66540af33486d37","schema_version":"1.0","event_id":"sha256:88f15b97b0b556bbdceda272f531b9855c671cd970a2c334a66540af33486d37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6RSYEFYJ5CJA5HYWOYUNNWLJXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.GR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Darius Petermann, Mahdi M. Kalayeh","submitted_at":"2025-01-09T18:13:57Z","abstract_excerpt":"Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is inherent to them. In this work, we hypothesize that insisting on the absolute need for ground truth audio-visual correspondence, is not only unnecessary, but also leads to severe restrictions in scale, quality, and diversity of the data, ultimately impairing its use in the modern generative models. That is, we propose a scalable image sonification framework w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05413","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/2501.05413/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":"2026-07-05T09:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X6PLLooEi1OgVw+RNdwiUCzA5TNDOBKKYE5i4AGinPwWPEyJBl4r0DQv49LnrdB/5XwOXSgqWsZ4S/iBfvw3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:48:45.369344Z"},"content_sha256":"b974f7ffc5867f61547b89284fdcfc7fe534f3ea0292af9eb32aa25783c4d456","schema_version":"1.0","event_id":"sha256:b974f7ffc5867f61547b89284fdcfc7fe534f3ea0292af9eb32aa25783c4d456"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/bundle.json","state_url":"https://pith.science/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/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":"2026-08-20T20:48:45Z","links":{"resolver":"https://pith.science/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL","bundle":"https://pith.science/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/bundle.json","state":"https://pith.science/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RSYEFYJ5CJA5HYWOYUNNWLJXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6RSYEFYJ5CJA5HYWOYUNNWLJXL","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":"ec14bd32d60c53fe0d105453c74b516bc368eac2e9b7efa0ae6962336e36d2db","cross_cats_sorted":["cs.CV","cs.GR","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-09T18:13:57Z","title_canon_sha256":"fc153a50ec68dd2d409ccfa8abcb048105727e4e5cbf7acf22d3dc46d97ddb2b"},"schema_version":"1.0","source":{"id":"2501.05413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05413","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05413v1","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05413","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"6RSYEFYJ5CJA","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"6RSYEFYJ5CJA5HYW","created_at":"2026-07-05T09:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"6RSYEFYJ","created_at":"2026-07-05T09:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:b974f7ffc5867f61547b89284fdcfc7fe534f3ea0292af9eb32aa25783c4d456","target":"graph","created_at":"2026-07-05T09:59:09Z","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/2501.05413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is inherent to them. In this work, we hypothesize that insisting on the absolute need for ground truth audio-visual correspondence, is not only unnecessary, but also leads to severe restrictions in scale, quality, and diversity of the data, ultimately impairing its use in the modern generative models. That is, we propose a scalable image sonification framework w","authors_text":"Darius Petermann, Mahdi M. Kalayeh","cross_cats":["cs.CV","cs.GR","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-09T18:13:57Z","title":"Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05413","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":"sha256:88f15b97b0b556bbdceda272f531b9855c671cd970a2c334a66540af33486d37","target":"record","created_at":"2026-07-05T09:59:09Z","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":"ec14bd32d60c53fe0d105453c74b516bc368eac2e9b7efa0ae6962336e36d2db","cross_cats_sorted":["cs.CV","cs.GR","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-09T18:13:57Z","title_canon_sha256":"fc153a50ec68dd2d409ccfa8abcb048105727e4e5cbf7acf22d3dc46d97ddb2b"},"schema_version":"1.0","source":{"id":"2501.05413","kind":"arxiv","version":1}},"canonical_sha256":"f465821709e8920e9f167628d6d969bacf6494f9584a13b55484540d9f47d409","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f465821709e8920e9f167628d6d969bacf6494f9584a13b55484540d9f47d409","first_computed_at":"2026-07-05T09:59:09.579333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:09.579333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KvrfGgprOtmNo9Swy5FYcbOGx8kWBKTTDArrQjmOFtgqMeM62chJq+SBZaxcEfBl63YDKac8l8bDgeniAEwkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:09.579837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88f15b97b0b556bbdceda272f531b9855c671cd970a2c334a66540af33486d37","sha256:b974f7ffc5867f61547b89284fdcfc7fe534f3ea0292af9eb32aa25783c4d456"],"state_sha256":"f9c8e8be9687f1b3a9084ad5de4f7aa87099968b7eecb39a77e456d0632e6b24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aW3SldqP3RIAPcGDVBtn572BWseuubS7OjBrS0jRHjU9wAiv5gOYJzA4J7WCOBK6WVMHwwQAmR2nIhXiVgHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:48:45.374048Z","bundle_sha256":"661882abc6273d062332bd691b8a414573018783a00ab2c401ad1e4b9fa51141"}}