{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FWPIXZ6GIYRKYQHUXXT26IOWBL","short_pith_number":"pith:FWPIXZ6G","canonical_record":{"source":{"id":"2509.09717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-09T18:57:10Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"630548564d70e81648f7d09c3ede54b99686a2e24d9a059f4e26374e713e9af1","abstract_canon_sha256":"ddb8401f9c6e8ea1c6c33f80bfc9ed635adeb87dc7e45bb567fcdae2a9210131"},"schema_version":"1.0"},"canonical_sha256":"2d9e8be7c64622ac40f4bde7af21d60ac06c001ed1d8338a0e6e634e8a377208","source":{"kind":"arxiv","id":"2509.09717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09717","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09717v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09717","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"FWPIXZ6GIYRK","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"FWPIXZ6GIYRKYQHU","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"FWPIXZ6G","created_at":"2026-07-05T12:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FWPIXZ6GIYRKYQHUXXT26IOWBL","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-09T18:57:10Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"630548564d70e81648f7d09c3ede54b99686a2e24d9a059f4e26374e713e9af1","abstract_canon_sha256":"ddb8401f9c6e8ea1c6c33f80bfc9ed635adeb87dc7e45bb567fcdae2a9210131"},"schema_version":"1.0"},"canonical_sha256":"2d9e8be7c64622ac40f4bde7af21d60ac06c001ed1d8338a0e6e634e8a377208","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.741272Z","signature_b64":"CNkjO2r+zYtC0rWFtGkaL0wrh0xrzraNCxsNsc/zmCZRdzZLf8kaAy3ZevrUZ8xwjstDVhvSsIfLL3I3mlrnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9e8be7c64622ac40f4bde7af21d60ac06c001ed1d8338a0e6e634e8a377208","last_reissued_at":"2026-07-05T12:09:47.740673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.740673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09717","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":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rq/q8dip3rOrNcN23pT7yAP/VPKGJcgeIXq4INWiijmX0PLiOvK9xwQR9u0P7AmC6/HtmDI5HEsihvfhH1sEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:07:20.028346Z"},"content_sha256":"5c6df3073c2866fdfd8034a5f869c02ffb6e3b5acbfecce473d3ebf19be5cc3d","schema_version":"1.0","event_id":"sha256:5c6df3073c2866fdfd8034a5f869c02ffb6e3b5acbfecce473d3ebf19be5cc3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FWPIXZ6GIYRKYQHUXXT26IOWBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Testing chatbots on the creation of encoders for audio conditioned image generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jorge E. Le\\'on, Miguel Carrasco","submitted_at":"2025-09-09T18:57:10Z","abstract_excerpt":"On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual representations, even when there is clear evidence that audio can be employed as input as well. Given the previous, in this work, we explore whether state-of-the-art conversational agents can design effective audio encoders to replace the CLIP text encoder from Stable Diffusion 1.5, enabling image synthesis directly from sound. We prompted five publicly availab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09717","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/2509.09717/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":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xczCncDL7eCgf2G9dG6Nhb0oO9c3hy5vqBVhnWyyULXTj8S3SKHf4cZy6R6W4Nvs4lQQZOqHexFXUfNASMwzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:07:20.028860Z"},"content_sha256":"5ee611d3a0ef25e8b4d3c1b0a05a3d8f34236e4cfc576928b3b8b5d5071f0ce7","schema_version":"1.0","event_id":"sha256:5ee611d3a0ef25e8b4d3c1b0a05a3d8f34236e4cfc576928b3b8b5d5071f0ce7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/bundle.json","state_url":"https://pith.science/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/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":"2026-08-05T04:07:20Z","links":{"resolver":"https://pith.science/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL","bundle":"https://pith.science/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/bundle.json","state":"https://pith.science/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWPIXZ6GIYRKYQHUXXT26IOWBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FWPIXZ6GIYRKYQHUXXT26IOWBL","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":"ddb8401f9c6e8ea1c6c33f80bfc9ed635adeb87dc7e45bb567fcdae2a9210131","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-09T18:57:10Z","title_canon_sha256":"630548564d70e81648f7d09c3ede54b99686a2e24d9a059f4e26374e713e9af1"},"schema_version":"1.0","source":{"id":"2509.09717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09717","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09717v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09717","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"FWPIXZ6GIYRK","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"FWPIXZ6GIYRKYQHU","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"FWPIXZ6G","created_at":"2026-07-05T12:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:5ee611d3a0ef25e8b4d3c1b0a05a3d8f34236e4cfc576928b3b8b5d5071f0ce7","target":"graph","created_at":"2026-07-05T12:09:47Z","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/2509.09717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual representations, even when there is clear evidence that audio can be employed as input as well. Given the previous, in this work, we explore whether state-of-the-art conversational agents can design effective audio encoders to replace the CLIP text encoder from Stable Diffusion 1.5, enabling image synthesis directly from sound. We prompted five publicly availab","authors_text":"Jorge E. Le\\'on, Miguel Carrasco","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09717","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":"sha256:5c6df3073c2866fdfd8034a5f869c02ffb6e3b5acbfecce473d3ebf19be5cc3d","target":"record","created_at":"2026-07-05T12:09:47Z","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":"ddb8401f9c6e8ea1c6c33f80bfc9ed635adeb87dc7e45bb567fcdae2a9210131","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-09T18:57:10Z","title_canon_sha256":"630548564d70e81648f7d09c3ede54b99686a2e24d9a059f4e26374e713e9af1"},"schema_version":"1.0","source":{"id":"2509.09717","kind":"arxiv","version":1}},"canonical_sha256":"2d9e8be7c64622ac40f4bde7af21d60ac06c001ed1d8338a0e6e634e8a377208","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d9e8be7c64622ac40f4bde7af21d60ac06c001ed1d8338a0e6e634e8a377208","first_computed_at":"2026-07-05T12:09:47.740673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:47.740673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CNkjO2r+zYtC0rWFtGkaL0wrh0xrzraNCxsNsc/zmCZRdzZLf8kaAy3ZevrUZ8xwjstDVhvSsIfLL3I3mlrnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:47.741272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c6df3073c2866fdfd8034a5f869c02ffb6e3b5acbfecce473d3ebf19be5cc3d","sha256:5ee611d3a0ef25e8b4d3c1b0a05a3d8f34236e4cfc576928b3b8b5d5071f0ce7"],"state_sha256":"0f8c223011144dbbcf9c0a1da39b5843c22395f299f58be52edc28422cb30a13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oar28WgFGxcY9GG8ZmoWDsGS1kqxDvCJfVyKPOBOzzUZ7/KVosD49htcKydEuP7dwmANjhMZ7TNpBfmR458OCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:07:20.033678Z","bundle_sha256":"11526d852e27b5a908eab6b9ce1d4fab91d3a4322d60a7d422b7c9de85992393"}}