{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LKFSZVF5YN3PUWPAE3D2TWXW5G","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":"4d509eb96d86ff5bfec5db38cc2b94065e31b1bcbe717f46d432ff8bf934e2bb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-18T23:55:13Z","title_canon_sha256":"81bf92e32200a696b16ad41617b9bd801a482bfbe6b36f2d9a4771572a679861"},"schema_version":"1.0","source":{"id":"2211.10539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10539","created_at":"2026-07-05T05:43:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10539v2","created_at":"2026-07-05T05:43:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10539","created_at":"2026-07-05T05:43:35Z"},{"alias_kind":"pith_short_12","alias_value":"LKFSZVF5YN3P","created_at":"2026-07-05T05:43:35Z"},{"alias_kind":"pith_short_16","alias_value":"LKFSZVF5YN3PUWPA","created_at":"2026-07-05T05:43:35Z"},{"alias_kind":"pith_short_8","alias_value":"LKFSZVF5","created_at":"2026-07-05T05:43:35Z"}],"graph_snapshots":[{"event_id":"sha256:26b7d55a8c53b31f10531266ca48c7226c7a63b475aadac1f4b691a7e51f0fbf","target":"graph","created_at":"2026-07-05T05:43:35Z","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/2211.10539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the impact of visual assistance for automated audio captioning. Utilizing multi-encoder transformer architectures, which have previously been employed to introduce vision-related information in the context of sound event detection, we analyze the usefulness of incorporating a variety of pretrained features.\n  We perform experiments on a YouTube-based audiovisual data set and investigate the effect of applying the considered transfer learning technique in terms of a variety of captioning metrics.\n  We find that only one of the considered kinds of pretrained features provides consistent","authors_text":"Hugo Van hamme, Wim Boes","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-18T23:55:13Z","title":"Impact of visual assistance for automated audio captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10539","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":"sha256:406291759b4f08d22cdd679c05040feee0ae7b516c3e5bfb37a192b40defcf98","target":"record","created_at":"2026-07-05T05:43:35Z","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":"4d509eb96d86ff5bfec5db38cc2b94065e31b1bcbe717f46d432ff8bf934e2bb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-18T23:55:13Z","title_canon_sha256":"81bf92e32200a696b16ad41617b9bd801a482bfbe6b36f2d9a4771572a679861"},"schema_version":"1.0","source":{"id":"2211.10539","kind":"arxiv","version":2}},"canonical_sha256":"5a8b2cd4bdc376fa59e026c7a9daf6e9b0bc8872a229785a5b15790bb93badd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a8b2cd4bdc376fa59e026c7a9daf6e9b0bc8872a229785a5b15790bb93badd7","first_computed_at":"2026-07-05T05:43:35.627703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:35.627703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jS0cOp7ItT4g0dSkmfLyVxH8zDy9MJpBZfmzdvnPJSj/A9ZSKXBMmfrLfmu1Y34N395AlJVC67fZekMzLylADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:35.628075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:406291759b4f08d22cdd679c05040feee0ae7b516c3e5bfb37a192b40defcf98","sha256:26b7d55a8c53b31f10531266ca48c7226c7a63b475aadac1f4b691a7e51f0fbf"],"state_sha256":"1725d1b3cc1a8fb3e69fc646990630995107ef26a67108f7601aac373819da5b"}