{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VQPY2WLH7RO3OPOCDDRWYW5VVA","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":"a131cbb8dc9250cecfc2871538551412636cf225a17d836f41e0bee51b1dc838","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T16:57:44Z","title_canon_sha256":"8d3171b5b22074b46baf5e4767476591edfc7651569696535e10709c4173df29"},"schema_version":"1.0","source":{"id":"2007.12130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12130","created_at":"2026-07-05T01:21:43Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12130v1","created_at":"2026-07-05T01:21:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12130","created_at":"2026-07-05T01:21:43Z"},{"alias_kind":"pith_short_12","alias_value":"VQPY2WLH7RO3","created_at":"2026-07-05T01:21:43Z"},{"alias_kind":"pith_short_16","alias_value":"VQPY2WLH7RO3OPOC","created_at":"2026-07-05T01:21:43Z"},{"alias_kind":"pith_short_8","alias_value":"VQPY2WLH","created_at":"2026-07-05T01:21:43Z"}],"graph_snapshots":[{"event_id":"sha256:65d4d107e54b8b60b0369c7670ba954ec5ecd0051858d95b0954453d859b1eaf","target":"graph","created_at":"2026-07-05T01:21:43Z","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/2007.12130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this problem in the context of audio-conditioned visual synthesis -- a task that is important, for example, in occlusion reasoning. Specifically, our goal is to generate future video frames and their motion dynamics conditioned on audio and a few past frames. To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of aud","authors_text":"Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T16:57:44Z","title":"Sound2Sight: Generating Visual Dynamics from Sound and Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12130","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":"sha256:85d10c57489c0e6b0e92ab2f372484d75a394352039597c17766471e7e174e29","target":"record","created_at":"2026-07-05T01:21:43Z","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":"a131cbb8dc9250cecfc2871538551412636cf225a17d836f41e0bee51b1dc838","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T16:57:44Z","title_canon_sha256":"8d3171b5b22074b46baf5e4767476591edfc7651569696535e10709c4173df29"},"schema_version":"1.0","source":{"id":"2007.12130","kind":"arxiv","version":1}},"canonical_sha256":"ac1f8d5967fc5db73dc218e36c5bb5a80bf4f5ead599ddf7edfadf5f0001aaa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac1f8d5967fc5db73dc218e36c5bb5a80bf4f5ead599ddf7edfadf5f0001aaa9","first_computed_at":"2026-07-05T01:21:43.688522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:21:43.688522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+skMrUwTombfI/a1qEWm2ah1tNz1xUm2usF+j6/u4+2SuvPsrISPGODu69hgTC+qEjOkw/cAT0OximPY/aFKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:21:43.688900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.12130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85d10c57489c0e6b0e92ab2f372484d75a394352039597c17766471e7e174e29","sha256:65d4d107e54b8b60b0369c7670ba954ec5ecd0051858d95b0954453d859b1eaf"],"state_sha256":"ed06987316a2ef4579fae483cab0ddb8eb7df9decc5596436d33a0eba5c46f7f"}