{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F2TXRWI77TM5CRKBTTNZ3ZNJDW","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":"ef2447ad44eec2c5f51af07270130ad9a3c38d8cace86abc3405b27b14ba658b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-12T06:14:20Z","title_canon_sha256":"0c27b0c9a2863a403975f335ad32d7c9e2c834d43c4942bec1a343a3fae54468"},"schema_version":"1.0","source":{"id":"2208.06127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06127","created_at":"2026-07-05T04:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06127v1","created_at":"2026-07-05T04:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06127","created_at":"2026-07-05T04:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"F2TXRWI77TM5","created_at":"2026-07-05T04:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"F2TXRWI77TM5CRKB","created_at":"2026-07-05T04:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"F2TXRWI7","created_at":"2026-07-05T04:48:01Z"}],"graph_snapshots":[{"event_id":"sha256:88d0a09074e3a7c3c39c719ac7b5dedf14872add2b429b12b0146cdaa872405d","target":"graph","created_at":"2026-07-05T04:48:01Z","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/2208.06127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio captioning is a task that generates description of audio based on content. Pre-trained models are widely used in audio captioning due to high complexity. Unless a comprehensive system is re-trained, it is hard to determine how well pre-trained models contribute to audio captioning system. To prevent the time consuming and energy consuming process of retraining, it is necessary to propose a preditor of performance for the pre-trained model in audio captioning. In this paper, a series of pre-trained models are investigated for the correlation between extracted audio features and the perfor","authors_text":"Peiran Yan, Shengchen Li","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-12T06:14:20Z","title":"An investigation on selecting audio pre-trained models for audio captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06127","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":"sha256:55297d930bc5d0fcde46b9bc5eb2bc567b5011059fad199fe3002187bdc9510a","target":"record","created_at":"2026-07-05T04:48:01Z","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":"ef2447ad44eec2c5f51af07270130ad9a3c38d8cace86abc3405b27b14ba658b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-12T06:14:20Z","title_canon_sha256":"0c27b0c9a2863a403975f335ad32d7c9e2c834d43c4942bec1a343a3fae54468"},"schema_version":"1.0","source":{"id":"2208.06127","kind":"arxiv","version":1}},"canonical_sha256":"2ea778d91ffcd9d145419cdb9de5a91d85830db99321c119a6bc8e0e928ed392","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ea778d91ffcd9d145419cdb9de5a91d85830db99321c119a6bc8e0e928ed392","first_computed_at":"2026-07-05T04:48:01.464490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:01.464490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0vHS1PfyEqdVn3vwQwcYHUb2dU27iybmlAREVsozn6nPYgY/AGzvw+3ruprExzvKwGZSs03iihGyJhn/ZV7xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:01.464842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55297d930bc5d0fcde46b9bc5eb2bc567b5011059fad199fe3002187bdc9510a","sha256:88d0a09074e3a7c3c39c719ac7b5dedf14872add2b429b12b0146cdaa872405d"],"state_sha256":"d0f6e6be4316cdbb390d5d53815583a80a037fa55cf98327fe9f478539a50f49"}