{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:323L7T2PN5WY3BVTJGCFVEUF77","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":"281b02a32e7702439f219ffd402bff9e9c5082be8b345d2557a412a7a057890c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:59:56Z","title_canon_sha256":"d9b877f3d0ab11c81b1d00e11000bdbadf1bb62223d863ffb630842206b56cca"},"schema_version":"1.0","source":{"id":"2407.15850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15850","created_at":"2026-07-05T09:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15850v2","created_at":"2026-07-05T09:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15850","created_at":"2026-07-05T09:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"323L7T2PN5WY","created_at":"2026-07-05T09:38:49Z"},{"alias_kind":"pith_short_16","alias_value":"323L7T2PN5WY3BVT","created_at":"2026-07-05T09:38:49Z"},{"alias_kind":"pith_short_8","alias_value":"323L7T2P","created_at":"2026-07-05T09:38:49Z"}],"graph_snapshots":[{"event_id":"sha256:280376ff1d58961bff0863772fd1feaa418b60606139df7edae52cd3db464291","target":"graph","created_at":"2026-07-05T09:38:49Z","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/2407.15850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner. We use the power of off-the-shelf Visual-Language Models (VLMs) and Large Language Models (LLMs), and develop visual and text prompting strategies for this task. Our contributions are three-fold: (i) We demonstrate that a VLM can successfully name and refer to characters if directly prompted with character information through visual indications without requiring any fine-tuning; (ii) A two-stage process is developed to generate ADs, with the first stage asking the VLM to comprehensive","authors_text":"Andrew Zisserman, Arsha Nagrani, G\\\"ul Varol, Junyu Xie, Max Bain, Tengda Han, Weidi Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:59:56Z","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15850","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:a072372d3c638abc22ae134ddab54c3f48a5dfcb51ef9080f1c1d52df8b98a1d","target":"record","created_at":"2026-07-05T09:38:49Z","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":"281b02a32e7702439f219ffd402bff9e9c5082be8b345d2557a412a7a057890c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:59:56Z","title_canon_sha256":"d9b877f3d0ab11c81b1d00e11000bdbadf1bb62223d863ffb630842206b56cca"},"schema_version":"1.0","source":{"id":"2407.15850","kind":"arxiv","version":2}},"canonical_sha256":"deb6bfcf4f6f6d8d86b349845a9285ffe96392fb1c97e515b7f3e22d7b450b6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"deb6bfcf4f6f6d8d86b349845a9285ffe96392fb1c97e515b7f3e22d7b450b6d","first_computed_at":"2026-07-05T09:38:49.757182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:49.757182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vg9idLBkTCySsp08iavwYiC78rrSKWo884HDLOHYafFpo0pzyJF6/mrnV/MVKYhNzaVV2x7bBymog7M7OCUEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:49.757736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a072372d3c638abc22ae134ddab54c3f48a5dfcb51ef9080f1c1d52df8b98a1d","sha256:280376ff1d58961bff0863772fd1feaa418b60606139df7edae52cd3db464291"],"state_sha256":"4c15978df5343ff86e245aceb3f6fd805e034c64a42a347cd89b344767f79fa2"}