{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D5ODIZX7GQ32KQKV5UGFQ4GGYE","short_pith_number":"pith:D5ODIZX7","canonical_record":{"source":{"id":"2409.09401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T10:23:35Z","cross_cats_sorted":[],"title_canon_sha256":"0112aadfad9e4741d0d3d63c06247633ff9e46e5b137bf022afbe1b47e39db47","abstract_canon_sha256":"196d6210bb97a21c5658ae59932fd4df44a5f8f7ac4a1c2199b9f7acbaeec5f2"},"schema_version":"1.0"},"canonical_sha256":"1f5c3466ff3437a54155ed0c5870c6c11dd7886093287088a7f119a4037dc969","source":{"kind":"arxiv","id":"2409.09401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09401","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09401v2","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09401","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"D5ODIZX7GQ32","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"D5ODIZX7GQ32KQKV","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"D5ODIZX7","created_at":"2026-07-05T11:13:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D5ODIZX7GQ32KQKV5UGFQ4GGYE","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T10:23:35Z","cross_cats_sorted":[],"title_canon_sha256":"0112aadfad9e4741d0d3d63c06247633ff9e46e5b137bf022afbe1b47e39db47","abstract_canon_sha256":"196d6210bb97a21c5658ae59932fd4df44a5f8f7ac4a1c2199b9f7acbaeec5f2"},"schema_version":"1.0"},"canonical_sha256":"1f5c3466ff3437a54155ed0c5870c6c11dd7886093287088a7f119a4037dc969","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:12.600818Z","signature_b64":"Sjn97zp4ekXl2qhnd8euzvfkVWh8MlU7QoZqmmL+4DMen7QaZryqb+A2HqBpEgMyNWsH2VKQpsfz19NPX0jFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f5c3466ff3437a54155ed0c5870c6c11dd7886093287088a7f119a4037dc969","last_reissued_at":"2026-07-05T11:13:12.600261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:12.600261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09401","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":"2026-07-05T11:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCuDkAK7AyxeLHFya/TNA9LEFgTLW7e2kJcZQT0sVBgH62rwn4uIkzAbq9nMly+PTdUbS4tbmb+zpMrxibsmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:44:04.110216Z"},"content_sha256":"9c32fc1255f92f4f0651ee6157031ddcb16a0848fa6b256c174ffd67a1ec8bb7","schema_version":"1.0","event_id":"sha256:9c32fc1255f92f4f0651ee6157031ddcb16a0848fa6b256c174ffd67a1ec8bb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D5ODIZX7GQ32KQKV5UGFQ4GGYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Diverse and Efficient Audio Captioning via Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Ruibo Fu, Wei Liang, Xinyi Tu, Yong Ren","submitted_at":"2024-09-14T10:23:35Z","abstract_excerpt":"We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable success in various captioning tasks, their insufficient performance in terms of generation speed and diversity impede progress in audio understanding and multimedia applications. Our diffusion-based framework offers unique advantages stemming from its inherent stochasticity and holistic context modeling in captioning. Through rigorous evaluation, we demonstrate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09401","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/2409.09401/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":"2026-07-05T11:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6cJP96LgXvgHT7pgW7JqMqYNHPMFXmfBS6Jw3Z0r1recL/NN+l+PDD83g/lTw/FV9zSWBxEnIf0PPSejUXNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:44:04.110803Z"},"content_sha256":"2fb255000f1b977fca9beb1f806168bc73c217fc6cb442660cbcc0fabf8b7d6b","schema_version":"1.0","event_id":"sha256:2fb255000f1b977fca9beb1f806168bc73c217fc6cb442660cbcc0fabf8b7d6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/bundle.json","state_url":"https://pith.science/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/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":"2026-08-20T07:44:04Z","links":{"resolver":"https://pith.science/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE","bundle":"https://pith.science/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/bundle.json","state":"https://pith.science/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5ODIZX7GQ32KQKV5UGFQ4GGYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D5ODIZX7GQ32KQKV5UGFQ4GGYE","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":"196d6210bb97a21c5658ae59932fd4df44a5f8f7ac4a1c2199b9f7acbaeec5f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T10:23:35Z","title_canon_sha256":"0112aadfad9e4741d0d3d63c06247633ff9e46e5b137bf022afbe1b47e39db47"},"schema_version":"1.0","source":{"id":"2409.09401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09401","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09401v2","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09401","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"D5ODIZX7GQ32","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"D5ODIZX7GQ32KQKV","created_at":"2026-07-05T11:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"D5ODIZX7","created_at":"2026-07-05T11:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:2fb255000f1b977fca9beb1f806168bc73c217fc6cb442660cbcc0fabf8b7d6b","target":"graph","created_at":"2026-07-05T11:13:12Z","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/2409.09401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable success in various captioning tasks, their insufficient performance in terms of generation speed and diversity impede progress in audio understanding and multimedia applications. Our diffusion-based framework offers unique advantages stemming from its inherent stochasticity and holistic context modeling in captioning. Through rigorous evaluation, we demonstrate th","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Ruibo Fu, Wei Liang, Xinyi Tu, Yong Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T10:23:35Z","title":"Towards Diverse and Efficient Audio Captioning via Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09401","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":"sha256:9c32fc1255f92f4f0651ee6157031ddcb16a0848fa6b256c174ffd67a1ec8bb7","target":"record","created_at":"2026-07-05T11:13:12Z","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":"196d6210bb97a21c5658ae59932fd4df44a5f8f7ac4a1c2199b9f7acbaeec5f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T10:23:35Z","title_canon_sha256":"0112aadfad9e4741d0d3d63c06247633ff9e46e5b137bf022afbe1b47e39db47"},"schema_version":"1.0","source":{"id":"2409.09401","kind":"arxiv","version":2}},"canonical_sha256":"1f5c3466ff3437a54155ed0c5870c6c11dd7886093287088a7f119a4037dc969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f5c3466ff3437a54155ed0c5870c6c11dd7886093287088a7f119a4037dc969","first_computed_at":"2026-07-05T11:13:12.600261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:12.600261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sjn97zp4ekXl2qhnd8euzvfkVWh8MlU7QoZqmmL+4DMen7QaZryqb+A2HqBpEgMyNWsH2VKQpsfz19NPX0jFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:12.600818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c32fc1255f92f4f0651ee6157031ddcb16a0848fa6b256c174ffd67a1ec8bb7","sha256:2fb255000f1b977fca9beb1f806168bc73c217fc6cb442660cbcc0fabf8b7d6b"],"state_sha256":"bef14bb20f43d40e35251630a03aa901616bfaf98c031b268d726481ac017940"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6p6ZedMmMef30egtaZxvnzoPD9Wx5lPbnHxzh0Y8xeYSpAMAo4Gpwgp8MCD8TjtF3s2kj4HvrfCjnFZNuMWzCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:44:04.116018Z","bundle_sha256":"454826d49e80668e1b4ff607a604f016b3b9ccb7979de1ef6d2e3c16a82594e7"}}