{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3GAIAF2TAUFMZKANXWVCNJ37LJ","short_pith_number":"pith:3GAIAF2T","canonical_record":{"source":{"id":"2110.04684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-10T02:34:40Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"4d279d3b1b1129f464b802a5ed0dc0734ec1d63a8e007afbbde5b863043e25de","abstract_canon_sha256":"024d13f6b7182922fe51ecc318c836f76ec399c6c33dff283ae34f1f2f57f19d"},"schema_version":"1.0"},"canonical_sha256":"d980801753050acca80dbdaa26a77f5a4f01558539171ea8d91e908d7ae0ef43","source":{"kind":"arxiv","id":"2110.04684","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04684","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04684v2","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04684","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_12","alias_value":"3GAIAF2TAUFM","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_16","alias_value":"3GAIAF2TAUFMZKAN","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_8","alias_value":"3GAIAF2T","created_at":"2026-07-05T03:51:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3GAIAF2TAUFMZKANXWVCNJ37LJ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-10T02:34:40Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"4d279d3b1b1129f464b802a5ed0dc0734ec1d63a8e007afbbde5b863043e25de","abstract_canon_sha256":"024d13f6b7182922fe51ecc318c836f76ec399c6c33dff283ae34f1f2f57f19d"},"schema_version":"1.0"},"canonical_sha256":"d980801753050acca80dbdaa26a77f5a4f01558539171ea8d91e908d7ae0ef43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:56.994233Z","signature_b64":"bgb0ZNr/43wAhyjYx9PAGkB9MwOUZh/bQYqhGFvVzuiJ+2UDHH/+Glw3pYl7h0Pn+eKZwcMmhEI5+Rp6Rgk5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d980801753050acca80dbdaa26a77f5a4f01558539171ea8d91e908d7ae0ef43","last_reissued_at":"2026-07-05T03:51:56.993843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:56.993843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04684","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":"2026-07-05T03:51:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yhHSHvIfLh42M4lml/VjNuhq67TrAGmK/hjmQLEjwrmyT3/X4UDdlb0k48CnVNcNf1D7YVl8Juc4aJFEvECDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:20:18.700411Z"},"content_sha256":"4026075a2b057927cb3bc510dce6969b881cf36488a7f0e9e639b7afd2a73976","schema_version":"1.0","event_id":"sha256:4026075a2b057927cb3bc510dce6969b881cf36488a7f0e9e639b7afd2a73976"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3GAIAF2TAUFMZKANXWVCNJ37LJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kenny Q. Zhu, Mengyue Wu, Xuenan Xu, Zelin Zhou, Zeyu Xie, Zhiling Zhang","submitted_at":"2021-10-10T02:34:40Z","abstract_excerpt":"Automated audio captioning aims at generating textual descriptions for an audio clip. To evaluate the quality of generated audio captions, previous works directly adopt image captioning metrics like SPICE and CIDEr, without justifying their suitability in this new domain, which may mislead the development of advanced models. This problem is still unstudied due to the lack of human judgment datasets on caption quality. Therefore, we firstly construct two evaluation benchmarks, AudioCaps-Eval and Clotho-Eval. They are established with pairwise comparison instead of absolute rating to achieve bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04684","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/2110.04684/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":"2026-07-05T03:51:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBCXBnUoRCw2mzhMUxTV7ZaE2EMlcOnR9Wp1yghFDopbLmuBkzRt2QtJREbSO0lJSU+og/3cOS8CTK0So2yjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:20:18.700791Z"},"content_sha256":"28ee2b6b7d6bb539bc0dfa0cda9774739c4001a9d4b37471a13f2117053063b1","schema_version":"1.0","event_id":"sha256:28ee2b6b7d6bb539bc0dfa0cda9774739c4001a9d4b37471a13f2117053063b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/bundle.json","state_url":"https://pith.science/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/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":"2026-07-17T02:20:18Z","links":{"resolver":"https://pith.science/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ","bundle":"https://pith.science/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/bundle.json","state":"https://pith.science/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GAIAF2TAUFMZKANXWVCNJ37LJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3GAIAF2TAUFMZKANXWVCNJ37LJ","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":"024d13f6b7182922fe51ecc318c836f76ec399c6c33dff283ae34f1f2f57f19d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-10T02:34:40Z","title_canon_sha256":"4d279d3b1b1129f464b802a5ed0dc0734ec1d63a8e007afbbde5b863043e25de"},"schema_version":"1.0","source":{"id":"2110.04684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04684","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04684v2","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04684","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_12","alias_value":"3GAIAF2TAUFM","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_16","alias_value":"3GAIAF2TAUFMZKAN","created_at":"2026-07-05T03:51:56Z"},{"alias_kind":"pith_short_8","alias_value":"3GAIAF2T","created_at":"2026-07-05T03:51:56Z"}],"graph_snapshots":[{"event_id":"sha256:28ee2b6b7d6bb539bc0dfa0cda9774739c4001a9d4b37471a13f2117053063b1","target":"graph","created_at":"2026-07-05T03:51:56Z","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/2110.04684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning aims at generating textual descriptions for an audio clip. To evaluate the quality of generated audio captions, previous works directly adopt image captioning metrics like SPICE and CIDEr, without justifying their suitability in this new domain, which may mislead the development of advanced models. This problem is still unstudied due to the lack of human judgment datasets on caption quality. Therefore, we firstly construct two evaluation benchmarks, AudioCaps-Eval and Clotho-Eval. They are established with pairwise comparison instead of absolute rating to achieve bet","authors_text":"Kenny Q. Zhu, Mengyue Wu, Xuenan Xu, Zelin Zhou, Zeyu Xie, Zhiling Zhang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-10T02:34:40Z","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04684","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":"sha256:4026075a2b057927cb3bc510dce6969b881cf36488a7f0e9e639b7afd2a73976","target":"record","created_at":"2026-07-05T03:51:56Z","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":"024d13f6b7182922fe51ecc318c836f76ec399c6c33dff283ae34f1f2f57f19d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-10T02:34:40Z","title_canon_sha256":"4d279d3b1b1129f464b802a5ed0dc0734ec1d63a8e007afbbde5b863043e25de"},"schema_version":"1.0","source":{"id":"2110.04684","kind":"arxiv","version":2}},"canonical_sha256":"d980801753050acca80dbdaa26a77f5a4f01558539171ea8d91e908d7ae0ef43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d980801753050acca80dbdaa26a77f5a4f01558539171ea8d91e908d7ae0ef43","first_computed_at":"2026-07-05T03:51:56.993843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:56.993843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bgb0ZNr/43wAhyjYx9PAGkB9MwOUZh/bQYqhGFvVzuiJ+2UDHH/+Glw3pYl7h0Pn+eKZwcMmhEI5+Rp6Rgk5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:56.994233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4026075a2b057927cb3bc510dce6969b881cf36488a7f0e9e639b7afd2a73976","sha256:28ee2b6b7d6bb539bc0dfa0cda9774739c4001a9d4b37471a13f2117053063b1"],"state_sha256":"6da88111e14df84aedf72a4c8e28bee22abc3a8a7ee538642f0456f34f2f2cf9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gbxcoPvAJg1S59ycZRka+qbguUJQkDuiCYOI78981gHkVwgdncKmTnZ1rcF03KyxyHWyCdeOQP35/RgPWxo8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:20:18.703296Z","bundle_sha256":"97936aca5c5ec4b05d558f3cab1f883735b5c3b2581d4af8afaee81514d38381"}}