{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TEBGGSQNJCDWFMJKMUU5SNCTAX","short_pith_number":"pith:TEBGGSQN","canonical_record":{"source":{"id":"2210.06354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T11:58:59Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2a990f878cb7bb53a4ca380436659ebc13c83bf5f5237582b9e96a07e8dc1ed4","abstract_canon_sha256":"e69d632774c57493271cede13e113db73705801ca2d89ca8052996270d679377"},"schema_version":"1.0"},"canonical_sha256":"9902634a0d488762b12a6529d9345305df999c337734c2b08a8d69cac60fc5a4","source":{"kind":"arxiv","id":"2210.06354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06354","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06354v1","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06354","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"TEBGGSQNJCDW","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"TEBGGSQNJCDWFMJK","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"TEBGGSQN","created_at":"2026-07-05T05:05:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TEBGGSQNJCDWFMJKMUU5SNCTAX","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T11:58:59Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2a990f878cb7bb53a4ca380436659ebc13c83bf5f5237582b9e96a07e8dc1ed4","abstract_canon_sha256":"e69d632774c57493271cede13e113db73705801ca2d89ca8052996270d679377"},"schema_version":"1.0"},"canonical_sha256":"9902634a0d488762b12a6529d9345305df999c337734c2b08a8d69cac60fc5a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:59.507159Z","signature_b64":"30CIC0Ubq4CutigYFtVc+nBH4hjP8/thZ4wNtDa4jf4tAdtr/CEbDm5vvRYK3v7uW2CMg6TdF3+W+6Dj7h9EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9902634a0d488762b12a6529d9345305df999c337734c2b08a8d69cac60fc5a4","last_reissued_at":"2026-07-05T05:05:59.506749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:59.506749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06354","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":"2026-07-05T05:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RS/YJmn+jSv3OBMcyyxPu1dAblr2EQzH5min3AoaCiRsi98j20tSYIr48kI8QaaReFg/naLo7NmDh13BUErAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:08:51.466029Z"},"content_sha256":"f7ad836f31ee9c3402cf0a7086839e44c06b5753edb706a80664966d8031d04c","schema_version":"1.0","event_id":"sha256:f7ad836f31ee9c3402cf0a7086839e44c06b5753edb706a80664966d8031d04c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TEBGGSQNJCDWFMJKMUU5SNCTAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rupayan Chakraborty, Sunil Kumar Kopparapu, Swapnil Bhosale","submitted_at":"2022-10-03T11:58:59Z","abstract_excerpt":"Automatic Audio Captioning (AAC) refers to the task of translating an audio sample into a natural language (NL) text that describes the audio events, source of the events and their relationships. Unlike NL text generation tasks, which rely on metrics like BLEU, ROUGE, METEOR based on lexical semantics for evaluation, the AAC evaluation metric requires an ability to map NL text (phrases) that correspond to similar sounds in addition lexical semantics. Current metrics used for evaluation of AAC tasks lack an understanding of the perceived properties of sound represented by text. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06354","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/2210.06354/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":"2026-07-05T05:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CP2SSh0RGZGm9+x+qUOPLLCMafrI00ssfypnuShXeTgWLw2sTfRqTBg2SGEJL2QDmzHFZ+DGZ70bpSLtI9n7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:08:51.466421Z"},"content_sha256":"b58b3c852fbc62adff6a65192c9e858f3fe56e9391d402d70963f1291ee7e129","schema_version":"1.0","event_id":"sha256:b58b3c852fbc62adff6a65192c9e858f3fe56e9391d402d70963f1291ee7e129"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/bundle.json","state_url":"https://pith.science/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/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":"2026-07-11T09:08:51Z","links":{"resolver":"https://pith.science/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX","bundle":"https://pith.science/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/bundle.json","state":"https://pith.science/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEBGGSQNJCDWFMJKMUU5SNCTAX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TEBGGSQNJCDWFMJKMUU5SNCTAX","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":"e69d632774c57493271cede13e113db73705801ca2d89ca8052996270d679377","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T11:58:59Z","title_canon_sha256":"2a990f878cb7bb53a4ca380436659ebc13c83bf5f5237582b9e96a07e8dc1ed4"},"schema_version":"1.0","source":{"id":"2210.06354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06354","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06354v1","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06354","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"TEBGGSQNJCDW","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"TEBGGSQNJCDWFMJK","created_at":"2026-07-05T05:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"TEBGGSQN","created_at":"2026-07-05T05:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:b58b3c852fbc62adff6a65192c9e858f3fe56e9391d402d70963f1291ee7e129","target":"graph","created_at":"2026-07-05T05:05:59Z","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/2210.06354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Audio Captioning (AAC) refers to the task of translating an audio sample into a natural language (NL) text that describes the audio events, source of the events and their relationships. Unlike NL text generation tasks, which rely on metrics like BLEU, ROUGE, METEOR based on lexical semantics for evaluation, the AAC evaluation metric requires an ability to map NL text (phrases) that correspond to similar sounds in addition lexical semantics. Current metrics used for evaluation of AAC tasks lack an understanding of the perceived properties of sound represented by text. In this paper, w","authors_text":"Rupayan Chakraborty, Sunil Kumar Kopparapu, Swapnil Bhosale","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T11:58:59Z","title":"Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06354","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:f7ad836f31ee9c3402cf0a7086839e44c06b5753edb706a80664966d8031d04c","target":"record","created_at":"2026-07-05T05:05:59Z","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":"e69d632774c57493271cede13e113db73705801ca2d89ca8052996270d679377","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T11:58:59Z","title_canon_sha256":"2a990f878cb7bb53a4ca380436659ebc13c83bf5f5237582b9e96a07e8dc1ed4"},"schema_version":"1.0","source":{"id":"2210.06354","kind":"arxiv","version":1}},"canonical_sha256":"9902634a0d488762b12a6529d9345305df999c337734c2b08a8d69cac60fc5a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9902634a0d488762b12a6529d9345305df999c337734c2b08a8d69cac60fc5a4","first_computed_at":"2026-07-05T05:05:59.506749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:59.506749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"30CIC0Ubq4CutigYFtVc+nBH4hjP8/thZ4wNtDa4jf4tAdtr/CEbDm5vvRYK3v7uW2CMg6TdF3+W+6Dj7h9EDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:59.507159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7ad836f31ee9c3402cf0a7086839e44c06b5753edb706a80664966d8031d04c","sha256:b58b3c852fbc62adff6a65192c9e858f3fe56e9391d402d70963f1291ee7e129"],"state_sha256":"d6cc042a33c87b8500366a5aae529da3d52166b7b3315005a525312ad1cdd62c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1FN5uqEnNOoKtDo9/p55HRxG7FQ87VA8kGXnUtrOwWN51IgSV8pgXMXNlqlKSBkl6sUCcC98rAEHS4XxzoKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T09:08:51.470595Z","bundle_sha256":"c5677fe4f6f45d4b5771506d2196d7ef82e4c591c3fe5ff201feeadd16b91ac3"}}