{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GZIUOG3BLQLSGHKRYHMGO2XNBJ","short_pith_number":"pith:GZIUOG3B","canonical_record":{"source":{"id":"2608.12549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T19:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"825789b2998f9099b2f1b04d58b7ea2384a3ea6ee9ff580ea64d9cfccadd2521","abstract_canon_sha256":"aeb450ee9aa160cbc75ddb36c9f3e14f7628e244dfd031e3250a01de5d2e582e"},"schema_version":"1.0"},"canonical_sha256":"3651471b615c17231d51c1d8676aed0a4bab4ced85de031ecc91d247df16d07b","source":{"kind":"arxiv","id":"2608.12549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12549","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12549v1","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12549","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"GZIUOG3BLQLS","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"GZIUOG3BLQLSGHKR","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"GZIUOG3B","created_at":"2026-08-14T00:44:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GZIUOG3BLQLSGHKRYHMGO2XNBJ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T19:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"825789b2998f9099b2f1b04d58b7ea2384a3ea6ee9ff580ea64d9cfccadd2521","abstract_canon_sha256":"aeb450ee9aa160cbc75ddb36c9f3e14f7628e244dfd031e3250a01de5d2e582e"},"schema_version":"1.0"},"canonical_sha256":"3651471b615c17231d51c1d8676aed0a4bab4ced85de031ecc91d247df16d07b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:44:46.002766Z","signature_b64":"0tFa2CbWAjSUEIBTv15xjW3CiRgS302CG+9EaIdDx+3FebMLITLF3NPAxdHSaaK1esa8aHA27gYrHo22mndRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3651471b615c17231d51c1d8676aed0a4bab4ced85de031ecc91d247df16d07b","last_reissued_at":"2026-08-14T00:44:45.993031Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:44:45.993031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12549","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":"2026-08-14T00:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6igY+amcOPdGdshRcuhA+qf6ruWATphSMCU32Q7AzUmL85Ova2QTayoPc9lbrsYniGoySCKyqXTWokI5wnRgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:22:02.674492Z"},"content_sha256":"0a7610ef611474667d82493e46fabe1396d10ef1d3fc59bd96956a6542427284","schema_version":"1.0","event_id":"sha256:0a7610ef611474667d82493e46fabe1396d10ef1d3fc59bd96956a6542427284"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GZIUOG3BLQLSGHKRYHMGO2XNBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Julian Spravil, Sebastian Houben, Sven Behnke","submitted_at":"2026-08-12T19:39:17Z","abstract_excerpt":"Visual content is the dominant medium of communication, yet without audio descriptions (ADs), it remains inaccessible to blind and low-vision people. ADs narrate context-relevant visual events during natural audio pauses. Manually creating ADs is expensive, limiting coverage to a small fraction of available content. Most existing automatic AD generation methods frame the task as video clip captioning, requiring ground-truth timestamps and additional context cues such as character databases. Current benchmarks reinforce this framing, consisting of short video segments paired with automatic or t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12549","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/2608.12549/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":"2026-08-14T00:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"weYOsjyyY045YclWE+kS9DlhJk/1rgB3clFtDfHpNCts+G0OyAL0zNnvHEi8Z+0wQ2XG1KMFd4cYczNYHdOWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:22:02.674986Z"},"content_sha256":"74b9ab1932c7635fdfa820d5205c6a8218ea794bf52dda87270bfa696d7f1028","schema_version":"1.0","event_id":"sha256:74b9ab1932c7635fdfa820d5205c6a8218ea794bf52dda87270bfa696d7f1028"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/bundle.json","state_url":"https://pith.science/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/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":"2026-08-24T03:22:02Z","links":{"resolver":"https://pith.science/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ","bundle":"https://pith.science/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/bundle.json","state":"https://pith.science/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZIUOG3BLQLSGHKRYHMGO2XNBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GZIUOG3BLQLSGHKRYHMGO2XNBJ","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":"aeb450ee9aa160cbc75ddb36c9f3e14f7628e244dfd031e3250a01de5d2e582e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T19:39:17Z","title_canon_sha256":"825789b2998f9099b2f1b04d58b7ea2384a3ea6ee9ff580ea64d9cfccadd2521"},"schema_version":"1.0","source":{"id":"2608.12549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12549","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12549v1","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12549","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"GZIUOG3BLQLS","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"GZIUOG3BLQLSGHKR","created_at":"2026-08-14T00:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"GZIUOG3B","created_at":"2026-08-14T00:44:45Z"}],"graph_snapshots":[{"event_id":"sha256:74b9ab1932c7635fdfa820d5205c6a8218ea794bf52dda87270bfa696d7f1028","target":"graph","created_at":"2026-08-14T00:44:45Z","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/2608.12549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual content is the dominant medium of communication, yet without audio descriptions (ADs), it remains inaccessible to blind and low-vision people. ADs narrate context-relevant visual events during natural audio pauses. Manually creating ADs is expensive, limiting coverage to a small fraction of available content. Most existing automatic AD generation methods frame the task as video clip captioning, requiring ground-truth timestamps and additional context cues such as character databases. Current benchmarks reinforce this framing, consisting of short video segments paired with automatic or t","authors_text":"Julian Spravil, Sebastian Houben, Sven Behnke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T19:39:17Z","title":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12549","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":"sha256:0a7610ef611474667d82493e46fabe1396d10ef1d3fc59bd96956a6542427284","target":"record","created_at":"2026-08-14T00:44:45Z","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":"aeb450ee9aa160cbc75ddb36c9f3e14f7628e244dfd031e3250a01de5d2e582e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T19:39:17Z","title_canon_sha256":"825789b2998f9099b2f1b04d58b7ea2384a3ea6ee9ff580ea64d9cfccadd2521"},"schema_version":"1.0","source":{"id":"2608.12549","kind":"arxiv","version":1}},"canonical_sha256":"3651471b615c17231d51c1d8676aed0a4bab4ced85de031ecc91d247df16d07b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3651471b615c17231d51c1d8676aed0a4bab4ced85de031ecc91d247df16d07b","first_computed_at":"2026-08-14T00:44:45.993031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:44:45.993031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0tFa2CbWAjSUEIBTv15xjW3CiRgS302CG+9EaIdDx+3FebMLITLF3NPAxdHSaaK1esa8aHA27gYrHo22mndRBQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:44:46.002766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a7610ef611474667d82493e46fabe1396d10ef1d3fc59bd96956a6542427284","sha256:74b9ab1932c7635fdfa820d5205c6a8218ea794bf52dda87270bfa696d7f1028"],"state_sha256":"e4eb368f65933a3df931a5e7e21a1119380b5bfe42577f72cc76efdebd857908"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdJ1fycmiVGWGn4Mv3Uy6HpMONpM3/ykgdKaRymRbDuUxifBLYPRdDqx0sJTO4cfG9IDfHsJDMVwR552z4PcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:22:02.680122Z","bundle_sha256":"f2c1865487a0ca4fe9452bde92c663b30fa63d398925cbc730c72d6ccc5b7a64"}}