{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:L245KBKEN5ZNANNXJL6K2YC7SU","short_pith_number":"pith:L245KBKE","canonical_record":{"source":{"id":"2102.11457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T02:09:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"22671d69319df897c570cb7dea898326d5e67a5cdd26c6c97e7bd31c1383c1cb","abstract_canon_sha256":"ea619abec621b713960e40f640bbebbd95397afd26e2876fbe16c1d74cebe875"},"schema_version":"1.0"},"canonical_sha256":"5eb9d505446f72d035b74afcad605f953ab5dab1472568cf7f754555ee333bd6","source":{"kind":"arxiv","id":"2102.11457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11457","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11457v1","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11457","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"L245KBKEN5ZN","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"L245KBKEN5ZNANNX","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"L245KBKE","created_at":"2026-07-05T02:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:L245KBKEN5ZNANNXJL6K2YC7SU","target":"record","payload":{"canonical_record":{"source":{"id":"2102.11457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T02:09:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"22671d69319df897c570cb7dea898326d5e67a5cdd26c6c97e7bd31c1383c1cb","abstract_canon_sha256":"ea619abec621b713960e40f640bbebbd95397afd26e2876fbe16c1d74cebe875"},"schema_version":"1.0"},"canonical_sha256":"5eb9d505446f72d035b74afcad605f953ab5dab1472568cf7f754555ee333bd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:11.778616Z","signature_b64":"K/EvDJWsYZl0FuDkhosNhg4BeUbDlo8TXN3OhSmJpGUbk8XyC+btxe2M7qf0YiWHQR5AraFBqvLtjxsMrB8iBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb9d505446f72d035b74afcad605f953ab5dab1472568cf7f754555ee333bd6","last_reissued_at":"2026-07-05T02:17:11.778096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:11.778096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.11457","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":"2026-07-05T02:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9c5SqAYxmKvfQvo5Lk96veBVuGGNkzEVfA5aMFKDhQq2A0ZoXEF0dXmCcNv8MKrFxyJjX0kgMrBA51dZNk8MDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T02:39:15.275041Z"},"content_sha256":"889d378c415d6296f2033b51a8100707561b3964d1d43551d43217cb7fb54c1d","schema_version":"1.0","event_id":"sha256:889d378c415d6296f2033b51a8100707561b3964d1d43551d43217cb7fb54c1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:L245KBKEN5ZNANNXJL6K2YC7SU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Xuenan Xu, Zeyu Xie","submitted_at":"2021-02-23T02:09:49Z","abstract_excerpt":"Automated audio captioning (AAC) aims at generating summarizing descriptions for audio clips. Multitudinous concepts are described in an audio caption, ranging from local information such as sound events to global information like acoustic scenery. Currently, the mainstream paradigm for AAC is the end-to-end encoder-decoder architecture, expecting the encoder to learn all levels of concepts embedded in the audio automatically. This paper first proposes a topic model for audio descriptions, comprehensively analyzing the hierarchical audio topics that are commonly covered. We then explore a tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11457","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/2102.11457/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":"2026-07-05T02:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKnjyOQn41z0Ygetwi04WauuZ3ifh6jFoEUDYqYItoKQO6fwPI4pYA8pTCzTEfKiAV1sCBkkXURbT7gbpcIXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T02:39:15.275449Z"},"content_sha256":"5563d4f89802a1283a163c08fe95c130bcdd92db60ae5dbbc8c024dc91b9101a","schema_version":"1.0","event_id":"sha256:5563d4f89802a1283a163c08fe95c130bcdd92db60ae5dbbc8c024dc91b9101a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L245KBKEN5ZNANNXJL6K2YC7SU/bundle.json","state_url":"https://pith.science/pith/L245KBKEN5ZNANNXJL6K2YC7SU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L245KBKEN5ZNANNXJL6K2YC7SU/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":"2026-07-16T02:39:15Z","links":{"resolver":"https://pith.science/pith/L245KBKEN5ZNANNXJL6K2YC7SU","bundle":"https://pith.science/pith/L245KBKEN5ZNANNXJL6K2YC7SU/bundle.json","state":"https://pith.science/pith/L245KBKEN5ZNANNXJL6K2YC7SU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L245KBKEN5ZNANNXJL6K2YC7SU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L245KBKEN5ZNANNXJL6K2YC7SU","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":"ea619abec621b713960e40f640bbebbd95397afd26e2876fbe16c1d74cebe875","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T02:09:49Z","title_canon_sha256":"22671d69319df897c570cb7dea898326d5e67a5cdd26c6c97e7bd31c1383c1cb"},"schema_version":"1.0","source":{"id":"2102.11457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11457","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11457v1","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11457","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"L245KBKEN5ZN","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"L245KBKEN5ZNANNX","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"L245KBKE","created_at":"2026-07-05T02:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:5563d4f89802a1283a163c08fe95c130bcdd92db60ae5dbbc8c024dc91b9101a","target":"graph","created_at":"2026-07-05T02:17:11Z","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/2102.11457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning (AAC) aims at generating summarizing descriptions for audio clips. Multitudinous concepts are described in an audio caption, ranging from local information such as sound events to global information like acoustic scenery. Currently, the mainstream paradigm for AAC is the end-to-end encoder-decoder architecture, expecting the encoder to learn all levels of concepts embedded in the audio automatically. This paper first proposes a topic model for audio descriptions, comprehensively analyzing the hierarchical audio topics that are commonly covered. We then explore a tran","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Xuenan Xu, Zeyu Xie","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T02:09:49Z","title":"Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11457","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":"sha256:889d378c415d6296f2033b51a8100707561b3964d1d43551d43217cb7fb54c1d","target":"record","created_at":"2026-07-05T02:17:11Z","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":"ea619abec621b713960e40f640bbebbd95397afd26e2876fbe16c1d74cebe875","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T02:09:49Z","title_canon_sha256":"22671d69319df897c570cb7dea898326d5e67a5cdd26c6c97e7bd31c1383c1cb"},"schema_version":"1.0","source":{"id":"2102.11457","kind":"arxiv","version":1}},"canonical_sha256":"5eb9d505446f72d035b74afcad605f953ab5dab1472568cf7f754555ee333bd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eb9d505446f72d035b74afcad605f953ab5dab1472568cf7f754555ee333bd6","first_computed_at":"2026-07-05T02:17:11.778096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:11.778096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/EvDJWsYZl0FuDkhosNhg4BeUbDlo8TXN3OhSmJpGUbk8XyC+btxe2M7qf0YiWHQR5AraFBqvLtjxsMrB8iBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:11.778616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.11457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:889d378c415d6296f2033b51a8100707561b3964d1d43551d43217cb7fb54c1d","sha256:5563d4f89802a1283a163c08fe95c130bcdd92db60ae5dbbc8c024dc91b9101a"],"state_sha256":"11508802e744a3ae9ff7927d0499bf9d3f52b12d63f3c2bb38af5ac0b9785e5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qIN8596IEK7dvWXB0znDhwbMV5lC08HoCk9fQtKaTOrbJGOwAx5Y2H/sT4rm+wWBrI3QaW6doaIedJ6OIHXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T02:39:15.277683Z","bundle_sha256":"3edc2f0dcbbd80e8df9ea2e13141b513043167cff46a4d4a97b38516c7ffc5c8"}}