{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ABMK4PHT6DDTYFYB7YR2Y5RQX2","short_pith_number":"pith:ABMK4PHT","schema_version":"1.0","canonical_sha256":"0058ae3cf3f0c73c1701fe23ac7630beb03f7730379959fd0a5bd6000293d922","source":{"kind":"arxiv","id":"2309.09836","version":2},"attestation_state":"computed","paper":{"title":"RECAP: Retrieval-Augmented Audio Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chandra Kiran Reddy Evuru, Dinesh Manocha, Ramani Duraiswami, Sonal Kumar, Sreyan Ghosh","submitted_at":"2023-09-18T14:53:08Z","abstract_excerpt":"We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention la"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.09836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T14:53:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"6ec24d7d6daec4c3dbdf2f5e4ddb556128fdfb6268d5b2d8240adae171923be9","abstract_canon_sha256":"96a26d9f1efa0f81b3ea490fdc8149af3cce04bd32b4f91feca70078b1f19181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:26.652724Z","signature_b64":"hW1BFmJ12W8xKVjdm47lZl1r92XC25+STdkjwzMvlgUQcFBs5/fqwhTptokMYcjK9cMXkJmhr83J+lLWIJWPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0058ae3cf3f0c73c1701fe23ac7630beb03f7730379959fd0a5bd6000293d922","last_reissued_at":"2026-07-05T08:28:26.652251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:26.652251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RECAP: Retrieval-Augmented Audio Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chandra Kiran Reddy Evuru, Dinesh Manocha, Ramani Duraiswami, Sonal Kumar, Sreyan Ghosh","submitted_at":"2023-09-18T14:53:08Z","abstract_excerpt":"We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09836","kind":"arxiv","version":2},"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/2309.09836/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.09836","created_at":"2026-07-05T08:28:26.652309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09836v2","created_at":"2026-07-05T08:28:26.652309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09836","created_at":"2026-07-05T08:28:26.652309+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABMK4PHT6DDT","created_at":"2026-07-05T08:28:26.652309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABMK4PHT6DDTYFYB","created_at":"2026-07-05T08:28:26.652309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABMK4PHT","created_at":"2026-07-05T08:28:26.652309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23323","citing_title":"Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2","json":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2.json","graph_json":"https://pith.science/api/pith-number/ABMK4PHT6DDTYFYB7YR2Y5RQX2/graph.json","events_json":"https://pith.science/api/pith-number/ABMK4PHT6DDTYFYB7YR2Y5RQX2/events.json","paper":"https://pith.science/paper/ABMK4PHT"},"agent_actions":{"view_html":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2","download_json":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2.json","view_paper":"https://pith.science/paper/ABMK4PHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09836&json=true","fetch_graph":"https://pith.science/api/pith-number/ABMK4PHT6DDTYFYB7YR2Y5RQX2/graph.json","fetch_events":"https://pith.science/api/pith-number/ABMK4PHT6DDTYFYB7YR2Y5RQX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2/action/storage_attestation","attest_author":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2/action/author_attestation","sign_citation":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2/action/citation_signature","submit_replication":"https://pith.science/pith/ABMK4PHT6DDTYFYB7YR2Y5RQX2/action/replication_record"}},"created_at":"2026-07-05T08:28:26.652309+00:00","updated_at":"2026-07-05T08:28:26.652309+00:00"}