{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q53S3PQA65SHDE6DCC3TOWI3E6","short_pith_number":"pith:Q53S3PQA","canonical_record":{"source":{"id":"2404.06309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T13:39:37Z","cross_cats_sorted":[],"title_canon_sha256":"1ac1c82ec3cb187d609cb3cac009205f6e7dba3d0dd373e8f7d826c4c135ab05","abstract_canon_sha256":"0747e89064ffe1137bb8131ce7a5d79eedc89ae687aeaf7d5c122cbd8aeb9bd0"},"schema_version":"1.0"},"canonical_sha256":"87772dbe00f7647193c310b737591b278a526c9b6b3b9268f4433f17e26c5067","source":{"kind":"arxiv","id":"2404.06309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06309","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06309v1","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06309","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"Q53S3PQA65SH","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"Q53S3PQA65SHDE6D","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"Q53S3PQA","created_at":"2026-07-05T08:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q53S3PQA65SHDE6DCC3TOWI3E6","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T13:39:37Z","cross_cats_sorted":[],"title_canon_sha256":"1ac1c82ec3cb187d609cb3cac009205f6e7dba3d0dd373e8f7d826c4c135ab05","abstract_canon_sha256":"0747e89064ffe1137bb8131ce7a5d79eedc89ae687aeaf7d5c122cbd8aeb9bd0"},"schema_version":"1.0"},"canonical_sha256":"87772dbe00f7647193c310b737591b278a526c9b6b3b9268f4433f17e26c5067","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:07.429196Z","signature_b64":"x2HR867LM7dJ66MCq62WXGNadzMP/QwbJ2rY5kt9vozJvOBAWOv9Py/NSZek3vGyjOWMRGbH8rJpTVM4UjIQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87772dbe00f7647193c310b737591b278a526c9b6b3b9268f4433f17e26c5067","last_reissued_at":"2026-07-05T08:06:07.428755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:07.428755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06309","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":"2026-07-05T08:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzLwoijeJvP0AKf7fQaQY9pGSBaVoENm4mNe8Mu9tZHqi6fVGiSTFusJ48YmjMHl88syNCrpp8cIUCUVVXoNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:15.094334Z"},"content_sha256":"3eec4ccf83295c5e4829ae0535356f8819d25a28dc2f868eee7a92a4a91bf6e1","schema_version":"1.0","event_id":"sha256:3eec4ccf83295c5e4829ae0535356f8819d25a28dc2f868eee7a92a4a91bf6e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q53S3PQA65SHDE6DCC3TOWI3E6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Sophia Koepke, David Kurzend\\\"orfer, Otniel-Bogdan Mercea, Zeynep Akata","submitted_at":"2024-04-09T13:39:37Z","abstract_excerpt":"Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as CLIP and CLAP. In this work, we explore such large pre-trained models to obtain features, i.e. CLIP for visual features, and CLAP for audio features. Furthermore, the CLIP and CLAP text encoders provide class label embeddings which are combined to boost the performance of the system. We propose a simple yet effective model that only relies on feed-forward neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06309","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/2404.06309/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":"2026-07-05T08:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OVw8anMZumnfvi5t+wweqhunLSGt8CNIGIdw60/sTInzGG+GFTGPrA9dHerE12lUu3g0mOn2A86eZrdpKJnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:15.094669Z"},"content_sha256":"983ecce4d615e184b04d4df329fdb0306f33da2414051be7d2c620b9cc2d12ca","schema_version":"1.0","event_id":"sha256:983ecce4d615e184b04d4df329fdb0306f33da2414051be7d2c620b9cc2d12ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/bundle.json","state_url":"https://pith.science/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/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":"2026-08-05T06:32:15Z","links":{"resolver":"https://pith.science/pith/Q53S3PQA65SHDE6DCC3TOWI3E6","bundle":"https://pith.science/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/bundle.json","state":"https://pith.science/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q53S3PQA65SHDE6DCC3TOWI3E6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q53S3PQA65SHDE6DCC3TOWI3E6","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":"0747e89064ffe1137bb8131ce7a5d79eedc89ae687aeaf7d5c122cbd8aeb9bd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T13:39:37Z","title_canon_sha256":"1ac1c82ec3cb187d609cb3cac009205f6e7dba3d0dd373e8f7d826c4c135ab05"},"schema_version":"1.0","source":{"id":"2404.06309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06309","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06309v1","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06309","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"Q53S3PQA65SH","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"Q53S3PQA65SHDE6D","created_at":"2026-07-05T08:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"Q53S3PQA","created_at":"2026-07-05T08:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:983ecce4d615e184b04d4df329fdb0306f33da2414051be7d2c620b9cc2d12ca","target":"graph","created_at":"2026-07-05T08:06:07Z","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/2404.06309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as CLIP and CLAP. In this work, we explore such large pre-trained models to obtain features, i.e. CLIP for visual features, and CLAP for audio features. Furthermore, the CLIP and CLAP text encoders provide class label embeddings which are combined to boost the performance of the system. We propose a simple yet effective model that only relies on feed-forward neur","authors_text":"A. Sophia Koepke, David Kurzend\\\"orfer, Otniel-Bogdan Mercea, Zeynep Akata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T13:39:37Z","title":"Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06309","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":"sha256:3eec4ccf83295c5e4829ae0535356f8819d25a28dc2f868eee7a92a4a91bf6e1","target":"record","created_at":"2026-07-05T08:06:07Z","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":"0747e89064ffe1137bb8131ce7a5d79eedc89ae687aeaf7d5c122cbd8aeb9bd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T13:39:37Z","title_canon_sha256":"1ac1c82ec3cb187d609cb3cac009205f6e7dba3d0dd373e8f7d826c4c135ab05"},"schema_version":"1.0","source":{"id":"2404.06309","kind":"arxiv","version":1}},"canonical_sha256":"87772dbe00f7647193c310b737591b278a526c9b6b3b9268f4433f17e26c5067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87772dbe00f7647193c310b737591b278a526c9b6b3b9268f4433f17e26c5067","first_computed_at":"2026-07-05T08:06:07.428755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:07.428755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2HR867LM7dJ66MCq62WXGNadzMP/QwbJ2rY5kt9vozJvOBAWOv9Py/NSZek3vGyjOWMRGbH8rJpTVM4UjIQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:07.429196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eec4ccf83295c5e4829ae0535356f8819d25a28dc2f868eee7a92a4a91bf6e1","sha256:983ecce4d615e184b04d4df329fdb0306f33da2414051be7d2c620b9cc2d12ca"],"state_sha256":"df5e4a7628731434ae50ad33da6dc6935d5cab8497f058e30d3a5599bbc7ad5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ttxe5788y0Wp6WWqnyCF/kwsgmsqIASIYXB+wRkAP1exWUxNDCOeTyOondB0Vn2lxZsM3B/HlnBhW95nrmrqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:32:15.097551Z","bundle_sha256":"01eb966ce3c8ac72adb77f52c07f31bfb6dbba04591f394e088c0380a9e092e1"}}