{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SMGIBDEO7XKA6DBQ55S2ZD66CV","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":"18278c098762a5a9f03e5bf44a2833e3356bd8ce27e96d0ba42bb50a57792ebe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T11:05:28Z","title_canon_sha256":"b24fbcaad77602f84762d91f6307ce6aefec7fa5cacce4668d6c8b51dc041d27"},"schema_version":"1.0","source":{"id":"2502.00397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00397","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00397v1","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00397","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"SMGIBDEO7XKA","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"SMGIBDEO7XKA6DBQ","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"SMGIBDEO","created_at":"2026-07-05T10:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:26b0c922bfc5f90add7d9a3a0d146611f1c741408fcf5688e8ef9c9706dfc965","target":"graph","created_at":"2026-07-05T10:08:33Z","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/2502.00397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces ViNet-S, a 36MB model based on the ViNet architecture with a U-Net design, featuring a lightweight decoder that significantly reduces model size and parameters without compromising performance. Additionally, ViNet-A (148MB) incorporates spatio-temporal action localization (STAL) features, differing from traditional video saliency models that use action classification backbones. Our studies show that an ensemble of ViNet-S and ViNet-A, by averaging predicted saliency maps, achieves state-of-the-art performance on three visual-only and six audio-visual saliency datasets, ou","authors_text":"Bhav Beri, Rohit Girmaji, Sarthak Bansal, Siddharth Jain, Vineet Gandhi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T11:05:28Z","title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00397","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":"sha256:0073514f491810b9658989ead8a05a3a7d0513154eaef0db90f0b70d3a11aa83","target":"record","created_at":"2026-07-05T10:08:33Z","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":"18278c098762a5a9f03e5bf44a2833e3356bd8ce27e96d0ba42bb50a57792ebe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T11:05:28Z","title_canon_sha256":"b24fbcaad77602f84762d91f6307ce6aefec7fa5cacce4668d6c8b51dc041d27"},"schema_version":"1.0","source":{"id":"2502.00397","kind":"arxiv","version":1}},"canonical_sha256":"930c808c8efdd40f0c30ef65ac8fde1546ddb8ba337d259fef9cfdd745ba3f53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"930c808c8efdd40f0c30ef65ac8fde1546ddb8ba337d259fef9cfdd745ba3f53","first_computed_at":"2026-07-05T10:08:33.170086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:33.170086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eRfQDHMtpe0uZlvjEVY3XStFgQnxBxfMWuI3MlmWRJ/grRa0pkz67+nwSkZ+uh6uZn7mHien2NWnnegerMBwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:33.170560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0073514f491810b9658989ead8a05a3a7d0513154eaef0db90f0b70d3a11aa83","sha256:26b0c922bfc5f90add7d9a3a0d146611f1c741408fcf5688e8ef9c9706dfc965"],"state_sha256":"1f58bd26b904edae3011582f8e9de95a9811d018c5c3a681207485f5da679ac5"}