{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HYYZ4ZSAJBDQG6AC26ZE6SRSBB","short_pith_number":"pith:HYYZ4ZSA","canonical_record":{"source":{"id":"2311.08396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T18:55:48Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"60e36268172cf67568801d99fb414dcd75022b0528b5c4a97ccbf75b788b157f","abstract_canon_sha256":"866cb17babe82bd6e132bda92bf2bd21555f8dd41a06dab4832031ad32007fec"},"schema_version":"1.0"},"canonical_sha256":"3e319e66404847037802d7b24f4a32086f046ae6d59443e3b6237a98a5372c6b","source":{"kind":"arxiv","id":"2311.08396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08396","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08396v1","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08396","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"HYYZ4ZSAJBDQ","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"HYYZ4ZSAJBDQG6AC","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"HYYZ4ZSA","created_at":"2026-07-05T07:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HYYZ4ZSAJBDQG6AC26ZE6SRSBB","target":"record","payload":{"canonical_record":{"source":{"id":"2311.08396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T18:55:48Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"60e36268172cf67568801d99fb414dcd75022b0528b5c4a97ccbf75b788b157f","abstract_canon_sha256":"866cb17babe82bd6e132bda92bf2bd21555f8dd41a06dab4832031ad32007fec"},"schema_version":"1.0"},"canonical_sha256":"3e319e66404847037802d7b24f4a32086f046ae6d59443e3b6237a98a5372c6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:44.532711Z","signature_b64":"NYeCBO0T6E/sLBHG4IQutsNy6mGpj4aSRy6DNxsuNUX8eR2n6dQ7Dw4cttse/kmfkQkuM/4u/kLcQcAJ4tIjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e319e66404847037802d7b24f4a32086f046ae6d59443e3b6237a98a5372c6b","last_reissued_at":"2026-07-05T07:12:44.532245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:44.532245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.08396","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":"2026-07-05T07:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfZ2UEduY3eRN09Z5m7K73HHn9srO0VvXjG2M7wge+SQrdtgamBWyN/RrQD94l5nR0Cv6ktMUUkG7940kyA7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:14:43.433236Z"},"content_sha256":"e94cf911d938042fc3a8036a2f2daa071d3d7d7b543de8d6cf6690daba8ed52b","schema_version":"1.0","event_id":"sha256:e94cf911d938042fc3a8036a2f2daa071d3d7d7b543de8d6cf6690daba8ed52b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HYYZ4ZSAJBDQG6AC26ZE6SRSBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"A. Sophia Koepke, Leonard Salewski, Stefan Fauth, Zeynep Akata","submitted_at":"2023-11-14T18:55:48Z","abstract_excerpt":"Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without prior training for this task. Different from speech recognition which translates audio content that contains spoken language into text, audio captioning is commonly concerned with ambient sounds, or sounds produced by a human performing an action. Inspired by zero-shot image captioning methods, we propose ZerAuCap, a novel framework for summarising such general audio signals in a text caption without requiring task-specific training. In particular, our framework exploits a pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08396","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/2311.08396/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":"2026-07-05T07:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvPrHR75TDx4rdfYSd87MnOppXa80QiM57ZgoQzv9tuX5m1a1godVQ/r5wJESKyUuP2X5+sEYZziRV42rLLhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:14:43.433863Z"},"content_sha256":"393e7acfebb2a75e335850e1da3de53a905ea7d175751273e7d6e8078d8d20cb","schema_version":"1.0","event_id":"sha256:393e7acfebb2a75e335850e1da3de53a905ea7d175751273e7d6e8078d8d20cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/bundle.json","state_url":"https://pith.science/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/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":"2026-08-07T05:14:43Z","links":{"resolver":"https://pith.science/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB","bundle":"https://pith.science/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/bundle.json","state":"https://pith.science/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYYZ4ZSAJBDQG6AC26ZE6SRSBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HYYZ4ZSAJBDQG6AC26ZE6SRSBB","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":"866cb17babe82bd6e132bda92bf2bd21555f8dd41a06dab4832031ad32007fec","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T18:55:48Z","title_canon_sha256":"60e36268172cf67568801d99fb414dcd75022b0528b5c4a97ccbf75b788b157f"},"schema_version":"1.0","source":{"id":"2311.08396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08396","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08396v1","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08396","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"HYYZ4ZSAJBDQ","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"HYYZ4ZSAJBDQG6AC","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"HYYZ4ZSA","created_at":"2026-07-05T07:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:393e7acfebb2a75e335850e1da3de53a905ea7d175751273e7d6e8078d8d20cb","target":"graph","created_at":"2026-07-05T07:12:44Z","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/2311.08396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without prior training for this task. Different from speech recognition which translates audio content that contains spoken language into text, audio captioning is commonly concerned with ambient sounds, or sounds produced by a human performing an action. Inspired by zero-shot image captioning methods, we propose ZerAuCap, a novel framework for summarising such general audio signals in a text caption without requiring task-specific training. In particular, our framework exploits a pre-tra","authors_text":"A. Sophia Koepke, Leonard Salewski, Stefan Fauth, Zeynep Akata","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T18:55:48Z","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08396","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:e94cf911d938042fc3a8036a2f2daa071d3d7d7b543de8d6cf6690daba8ed52b","target":"record","created_at":"2026-07-05T07:12:44Z","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":"866cb17babe82bd6e132bda92bf2bd21555f8dd41a06dab4832031ad32007fec","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T18:55:48Z","title_canon_sha256":"60e36268172cf67568801d99fb414dcd75022b0528b5c4a97ccbf75b788b157f"},"schema_version":"1.0","source":{"id":"2311.08396","kind":"arxiv","version":1}},"canonical_sha256":"3e319e66404847037802d7b24f4a32086f046ae6d59443e3b6237a98a5372c6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e319e66404847037802d7b24f4a32086f046ae6d59443e3b6237a98a5372c6b","first_computed_at":"2026-07-05T07:12:44.532245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:44.532245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYeCBO0T6E/sLBHG4IQutsNy6mGpj4aSRy6DNxsuNUX8eR2n6dQ7Dw4cttse/kmfkQkuM/4u/kLcQcAJ4tIjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:44.532711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e94cf911d938042fc3a8036a2f2daa071d3d7d7b543de8d6cf6690daba8ed52b","sha256:393e7acfebb2a75e335850e1da3de53a905ea7d175751273e7d6e8078d8d20cb"],"state_sha256":"98f57aa1f1c6b6e4f21b5e6bc5779d3ceea5e55b78638248aefa94b0be65b84d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYtKevY7vqevUpHOFUZ1QIPGtG8wvuOkoUBGi3yI4rFah6qR2CB6OO7IENmXVJNNfAwtviRruDL2M6o5ZWhBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:14:43.438901Z","bundle_sha256":"637111020813b5b2e98cc30d5fe0ba7b705df0051de6a587d057364a1bd5d2b6"}}