{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UKBLY2UBNSDS5YQ76F6IUYMTWL","short_pith_number":"pith:UKBLY2UB","canonical_record":{"source":{"id":"2505.13062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-19T12:52:51Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"aed9c34707f56f3612003fa158ec6970a7b7b2dcb890abed14ca0f19551e5097","abstract_canon_sha256":"cf64377df81c1382b3bdb6e3c3c466793c5e9720f7a4f8e8babc70eaef1fe3f5"},"schema_version":"1.0"},"canonical_sha256":"a282bc6a816c872ee21ff17c8a6193b2cbdc85fb79ca23c50eb0e0dd9721981a","source":{"kind":"arxiv","id":"2505.13062","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13062","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13062v3","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13062","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"UKBLY2UBNSDS","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"UKBLY2UBNSDS5YQ7","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"UKBLY2UB","created_at":"2026-07-05T11:10:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UKBLY2UBNSDS5YQ76F6IUYMTWL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-19T12:52:51Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"aed9c34707f56f3612003fa158ec6970a7b7b2dcb890abed14ca0f19551e5097","abstract_canon_sha256":"cf64377df81c1382b3bdb6e3c3c466793c5e9720f7a4f8e8babc70eaef1fe3f5"},"schema_version":"1.0"},"canonical_sha256":"a282bc6a816c872ee21ff17c8a6193b2cbdc85fb79ca23c50eb0e0dd9721981a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:56.600915Z","signature_b64":"OEgv1LTjqUjP80gIa3swNXx2dnvxsgIz7LRXmv6fYIYrb0v6/dVi3bcsyc1u4Mov23uCq+x1y7axnQBL91LrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a282bc6a816c872ee21ff17c8a6193b2cbdc85fb79ca23c50eb0e0dd9721981a","last_reissued_at":"2026-07-05T11:10:56.600377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:56.600377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13062","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tjlbGa9XDFiZsHT0g+eNJkwXXWP7FAZ6GkXOoCDtxmVnOWU1W+NgZK0QzbhPPLhelGkZPDwkrxegQ9C4n/XTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:35:07.782325Z"},"content_sha256":"dc80b4a1c9511986614f3d884836daaf2862eccc318d6191b9b9290583ce8417","schema_version":"1.0","event_id":"sha256:dc80b4a1c9511986614f3d884836daaf2862eccc318d6191b9b9290583ce8417"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UKBLY2UBNSDS5YQ76F6IUYMTWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chenxing Li, Dong Yu, Duzhen Zhang, Hao Gu, Le Xu, Manjie Xu, Ruibo Fu, Shan Yang, Yong Ren, Yujie Chen","submitted_at":"2025-05-19T12:52:51Z","abstract_excerpt":"Humans can intuitively infer sounds from silent videos, but whether multimodal large language models can perform modal-mismatch reasoning without accessing target modalities remains relatively unexplored. Current text-assisted-video-to-audio (VT2A) methods excel in video foley tasks but struggle to acquire audio descriptions during inference. We introduce the task of Reasoning Audio Descriptions from Silent Videos (SVAD) to address this challenge and investigate vision-language models' (VLMs) capabilities on this task. To further enhance the VLMs' reasoning capacity for the SVAD task, we const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13062","kind":"arxiv","version":3},"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/2505.13062/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":"2026-07-05T11:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4wKWCEGue/3cJCfmrn5q/gP/SeC0PBLZXYPuaTOH+UjsB0WlT46VQ/Jkq+sbGxu4Qn9xidDDF6IAbXBSBKwiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:35:07.783138Z"},"content_sha256":"cd4dd5f3736e09df624773b3cb224c883b9c5b5c519ca01799385665ef4c273c","schema_version":"1.0","event_id":"sha256:cd4dd5f3736e09df624773b3cb224c883b9c5b5c519ca01799385665ef4c273c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/bundle.json","state_url":"https://pith.science/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/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":"2026-08-16T10:35:07Z","links":{"resolver":"https://pith.science/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL","bundle":"https://pith.science/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/bundle.json","state":"https://pith.science/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKBLY2UBNSDS5YQ76F6IUYMTWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UKBLY2UBNSDS5YQ76F6IUYMTWL","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":"cf64377df81c1382b3bdb6e3c3c466793c5e9720f7a4f8e8babc70eaef1fe3f5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-19T12:52:51Z","title_canon_sha256":"aed9c34707f56f3612003fa158ec6970a7b7b2dcb890abed14ca0f19551e5097"},"schema_version":"1.0","source":{"id":"2505.13062","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13062","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13062v3","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13062","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"UKBLY2UBNSDS","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"UKBLY2UBNSDS5YQ7","created_at":"2026-07-05T11:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"UKBLY2UB","created_at":"2026-07-05T11:10:56Z"}],"graph_snapshots":[{"event_id":"sha256:cd4dd5f3736e09df624773b3cb224c883b9c5b5c519ca01799385665ef4c273c","target":"graph","created_at":"2026-07-05T11:10:56Z","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/2505.13062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can intuitively infer sounds from silent videos, but whether multimodal large language models can perform modal-mismatch reasoning without accessing target modalities remains relatively unexplored. Current text-assisted-video-to-audio (VT2A) methods excel in video foley tasks but struggle to acquire audio descriptions during inference. We introduce the task of Reasoning Audio Descriptions from Silent Videos (SVAD) to address this challenge and investigate vision-language models' (VLMs) capabilities on this task. To further enhance the VLMs' reasoning capacity for the SVAD task, we const","authors_text":"Chenxing Li, Dong Yu, Duzhen Zhang, Hao Gu, Le Xu, Manjie Xu, Ruibo Fu, Shan Yang, Yong Ren, Yujie Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-19T12:52:51Z","title":"Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13062","kind":"arxiv","version":3},"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:dc80b4a1c9511986614f3d884836daaf2862eccc318d6191b9b9290583ce8417","target":"record","created_at":"2026-07-05T11:10:56Z","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":"cf64377df81c1382b3bdb6e3c3c466793c5e9720f7a4f8e8babc70eaef1fe3f5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-19T12:52:51Z","title_canon_sha256":"aed9c34707f56f3612003fa158ec6970a7b7b2dcb890abed14ca0f19551e5097"},"schema_version":"1.0","source":{"id":"2505.13062","kind":"arxiv","version":3}},"canonical_sha256":"a282bc6a816c872ee21ff17c8a6193b2cbdc85fb79ca23c50eb0e0dd9721981a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a282bc6a816c872ee21ff17c8a6193b2cbdc85fb79ca23c50eb0e0dd9721981a","first_computed_at":"2026-07-05T11:10:56.600377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:56.600377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OEgv1LTjqUjP80gIa3swNXx2dnvxsgIz7LRXmv6fYIYrb0v6/dVi3bcsyc1u4Mov23uCq+x1y7axnQBL91LrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:56.600915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13062","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc80b4a1c9511986614f3d884836daaf2862eccc318d6191b9b9290583ce8417","sha256:cd4dd5f3736e09df624773b3cb224c883b9c5b5c519ca01799385665ef4c273c"],"state_sha256":"69433f59f0091ddca325f72a567a55ec67556002a47ff4d5831fe46a7be89d29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaGs6rDCVn0XQFnWZPkc958GjdtnIrIDMUBY6OKz5uiahq+7UHP3Yn0XPxz7aI3ruVZJcFbUF1LjmPTlYW8BAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:35:07.788568Z","bundle_sha256":"28adaeb7e619c1dc544518f9473cd5b0012c061a7b993ebc0d3db7519d22f9ec"}}