{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UFAP3XQOPVSKW5GKQZUKHPP6FY","short_pith_number":"pith:UFAP3XQO","canonical_record":{"source":{"id":"2304.13731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-24T07:45:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"f92702199b28281c4decdfe02603e061d166a4c94456fab4ac2386d3eedc59b0","abstract_canon_sha256":"0f930e5723049e693be9776d2453536b204e4d42db768510f9a4ac39582663a9"},"schema_version":"1.0"},"canonical_sha256":"a140fdde0e7d64ab74ca8668a3bdfe2e308693305dbdc30e05fe6be9b3b91a91","source":{"kind":"arxiv","id":"2304.13731","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13731","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13731v2","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13731","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"UFAP3XQOPVSK","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"UFAP3XQOPVSKW5GK","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"UFAP3XQO","created_at":"2026-07-05T06:14:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UFAP3XQOPVSKW5GKQZUKHPP6FY","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-24T07:45:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"f92702199b28281c4decdfe02603e061d166a4c94456fab4ac2386d3eedc59b0","abstract_canon_sha256":"0f930e5723049e693be9776d2453536b204e4d42db768510f9a4ac39582663a9"},"schema_version":"1.0"},"canonical_sha256":"a140fdde0e7d64ab74ca8668a3bdfe2e308693305dbdc30e05fe6be9b3b91a91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:42.392809Z","signature_b64":"D+4gN2Gnr6swWVke2jDz64d4tXNWIxtac4Dbb4G0o5OpoX1nmX2cOZmZtYPqXgqGaNKhSfRdjtr0OJGLxfMLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a140fdde0e7d64ab74ca8668a3bdfe2e308693305dbdc30e05fe6be9b3b91a91","last_reissued_at":"2026-07-05T06:14:42.392339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:42.392339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13731","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":"2026-07-05T06:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6MEONXo7YORlFpVtUpIT1H9z4w8UM5HpKhO7mvc6t77UTsVS/GZPkzTr2f+DQxlkRk3Yu0hunBrJ4Z9uJPzMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:31:49.862173Z"},"content_sha256":"712bd688f198e380172e2a9a64b1c86e60cc3e96fddf17c68bfadcdf87e1e8b8","schema_version":"1.0","event_id":"sha256:712bd688f198e380172e2a9a64b1c86e60cc3e96fddf17c68bfadcdf87e1e8b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UFAP3XQOPVSKW5GKQZUKHPP6FY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ambuj Mehrish, Deepanway Ghosal, Navonil Majumder, Soujanya Poria","submitted_at":"2023-04-24T07:45:28Z","abstract_excerpt":"The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural language processing (NLP) tasks. Inspired by such successes, we adopt such an instruction-tuned LLM Flan-T5 as the text encoder for text-to-audio (TTA) generation -- a task where the goal is to generate an audio from its textual description. The prior works on TTA either pre-trained a joint text-audio encoder or used a non-instruction-tuned model, such as, T5. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13731","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.13731/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":"2026-07-05T06:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Z1/32yZWevsYUKiBTTublWUNbEkpWmKpaia96BJPRpXlgB3odbkQvHiZlV2fWzv95qkDDEQSvINc53mhjWSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:31:49.862719Z"},"content_sha256":"71fc2f3dae72ad823154ca9c2a3971cda9eddf86db1a57f00419d5d9a26005de","schema_version":"1.0","event_id":"sha256:71fc2f3dae72ad823154ca9c2a3971cda9eddf86db1a57f00419d5d9a26005de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/bundle.json","state_url":"https://pith.science/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/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":"2026-08-19T08:31:49Z","links":{"resolver":"https://pith.science/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY","bundle":"https://pith.science/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/bundle.json","state":"https://pith.science/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFAP3XQOPVSKW5GKQZUKHPP6FY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UFAP3XQOPVSKW5GKQZUKHPP6FY","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":"0f930e5723049e693be9776d2453536b204e4d42db768510f9a4ac39582663a9","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-24T07:45:28Z","title_canon_sha256":"f92702199b28281c4decdfe02603e061d166a4c94456fab4ac2386d3eedc59b0"},"schema_version":"1.0","source":{"id":"2304.13731","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13731","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13731v2","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13731","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"UFAP3XQOPVSK","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"UFAP3XQOPVSKW5GK","created_at":"2026-07-05T06:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"UFAP3XQO","created_at":"2026-07-05T06:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:71fc2f3dae72ad823154ca9c2a3971cda9eddf86db1a57f00419d5d9a26005de","target":"graph","created_at":"2026-07-05T06:14:42Z","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/2304.13731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural language processing (NLP) tasks. Inspired by such successes, we adopt such an instruction-tuned LLM Flan-T5 as the text encoder for text-to-audio (TTA) generation -- a task where the goal is to generate an audio from its textual description. The prior works on TTA either pre-trained a joint text-audio encoder or used a non-instruction-tuned model, such as, T5. ","authors_text":"Ambuj Mehrish, Deepanway Ghosal, Navonil Majumder, Soujanya Poria","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-24T07:45:28Z","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13731","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":"sha256:712bd688f198e380172e2a9a64b1c86e60cc3e96fddf17c68bfadcdf87e1e8b8","target":"record","created_at":"2026-07-05T06:14:42Z","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":"0f930e5723049e693be9776d2453536b204e4d42db768510f9a4ac39582663a9","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-24T07:45:28Z","title_canon_sha256":"f92702199b28281c4decdfe02603e061d166a4c94456fab4ac2386d3eedc59b0"},"schema_version":"1.0","source":{"id":"2304.13731","kind":"arxiv","version":2}},"canonical_sha256":"a140fdde0e7d64ab74ca8668a3bdfe2e308693305dbdc30e05fe6be9b3b91a91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a140fdde0e7d64ab74ca8668a3bdfe2e308693305dbdc30e05fe6be9b3b91a91","first_computed_at":"2026-07-05T06:14:42.392339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:42.392339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+4gN2Gnr6swWVke2jDz64d4tXNWIxtac4Dbb4G0o5OpoX1nmX2cOZmZtYPqXgqGaNKhSfRdjtr0OJGLxfMLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:42.392809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13731","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:712bd688f198e380172e2a9a64b1c86e60cc3e96fddf17c68bfadcdf87e1e8b8","sha256:71fc2f3dae72ad823154ca9c2a3971cda9eddf86db1a57f00419d5d9a26005de"],"state_sha256":"7f4ea186e3afd4174775efb6e7974b4b1fbd801d4cd05549ca09dc3bf0726661"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ne4B8KnYP0TufFvtT4oemhZXBpVT6h7cWGcPNh/WxKVHSYkMchquf0xpbYKU/A4bfj8zzeZHRASpByQMczmDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:31:49.870233Z","bundle_sha256":"a99388d0b9790cb63ddcf4ad75d4f3889a4825a27ed205285243520fbfc8a9a2"}}