{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CR6R7L6EP6LV7QZYF6KMURDNPY","short_pith_number":"pith:CR6R7L6E","canonical_record":{"source":{"id":"2403.01226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-02T14:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"7b8224862376ca114bb7a77cc9ba96784230e8b5b2bc1e34f4446d45aa888eb4","abstract_canon_sha256":"79ce1ba28bfcdcb8a628b3adacd1f8ea867f1c628d73508f61d4add96d7e78d1"},"schema_version":"1.0"},"canonical_sha256":"147d1fafc47f975fc3382f94ca446d7e30b1767b85df7d4629bcb1af96f289e6","source":{"kind":"arxiv","id":"2403.01226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01226","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01226v1","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01226","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_12","alias_value":"CR6R7L6EP6LV","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_16","alias_value":"CR6R7L6EP6LV7QZY","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_8","alias_value":"CR6R7L6E","created_at":"2026-07-05T07:51:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CR6R7L6EP6LV7QZYF6KMURDNPY","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-02T14:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"7b8224862376ca114bb7a77cc9ba96784230e8b5b2bc1e34f4446d45aa888eb4","abstract_canon_sha256":"79ce1ba28bfcdcb8a628b3adacd1f8ea867f1c628d73508f61d4add96d7e78d1"},"schema_version":"1.0"},"canonical_sha256":"147d1fafc47f975fc3382f94ca446d7e30b1767b85df7d4629bcb1af96f289e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:44.102490Z","signature_b64":"If1xRaJrPQQltzcxeTGblfsnzHhPOGPSD2abPlhx9OEy9Wdfzunp0+woIjCLDccgjuuOUW57ZoGu3q4LkTOjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"147d1fafc47f975fc3382f94ca446d7e30b1767b85df7d4629bcb1af96f289e6","last_reissued_at":"2026-07-05T07:51:44.102077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:44.102077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01226","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":"2026-07-05T07:51:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zmTGQiOOg4YOmaxiCVD/KbiyfRXCDHvs1+0aSlks7vaFmbmfBUAHNzHoaZOls5P1GcJCI3WXLuz4KTkNRHzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:36:19.268518Z"},"content_sha256":"7398554ade85b28f46374581053eb651e44fb9eb9458f4ae3d859366bef09a23","schema_version":"1.0","event_id":"sha256:7398554ade85b28f46374581053eb651e44fb9eb9458f4ae3d859366bef09a23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CR6R7L6EP6LV7QZYF6KMURDNPY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanyue Li, Junwen Xiong, Peng Zhang, Tao You, Wei Huang, Yufei zha","submitted_at":"2024-03-02T14:52:58Z","abstract_excerpt":"Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising diffusion models have shown more promising in unifying task frameworks owing to their inherent ability of generalization. Following this motivation, a novel Diffusion architecture for generalized audio-visual Saliency prediction (DiffSal) is proposed in this work, which formulates the prediction problem as a conditional generative task of the saliency map by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01226","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/2403.01226/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":"2026-07-05T07:51:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6iYNACPL+csDYvuQIwVQQycSL12acpfBVXDIzHHzljsCB5965O6g3X9401nj+qIfMzv6+UnOBUVnwAjrwnocAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:36:19.269460Z"},"content_sha256":"fb32749cf3efad0e1bd629d6f6e83807dd1bbde6054c2b335b4b13d054198a9e","schema_version":"1.0","event_id":"sha256:fb32749cf3efad0e1bd629d6f6e83807dd1bbde6054c2b335b4b13d054198a9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/bundle.json","state_url":"https://pith.science/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/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":"2026-08-20T04:36:19Z","links":{"resolver":"https://pith.science/pith/CR6R7L6EP6LV7QZYF6KMURDNPY","bundle":"https://pith.science/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/bundle.json","state":"https://pith.science/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CR6R7L6EP6LV7QZYF6KMURDNPY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CR6R7L6EP6LV7QZYF6KMURDNPY","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":"79ce1ba28bfcdcb8a628b3adacd1f8ea867f1c628d73508f61d4add96d7e78d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-02T14:52:58Z","title_canon_sha256":"7b8224862376ca114bb7a77cc9ba96784230e8b5b2bc1e34f4446d45aa888eb4"},"schema_version":"1.0","source":{"id":"2403.01226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01226","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01226v1","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01226","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_12","alias_value":"CR6R7L6EP6LV","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_16","alias_value":"CR6R7L6EP6LV7QZY","created_at":"2026-07-05T07:51:44Z"},{"alias_kind":"pith_short_8","alias_value":"CR6R7L6E","created_at":"2026-07-05T07:51:44Z"}],"graph_snapshots":[{"event_id":"sha256:fb32749cf3efad0e1bd629d6f6e83807dd1bbde6054c2b335b4b13d054198a9e","target":"graph","created_at":"2026-07-05T07:51:44Z","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/2403.01226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising diffusion models have shown more promising in unifying task frameworks owing to their inherent ability of generalization. Following this motivation, a novel Diffusion architecture for generalized audio-visual Saliency prediction (DiffSal) is proposed in this work, which formulates the prediction problem as a conditional generative task of the saliency map by ","authors_text":"Chuanyue Li, Junwen Xiong, Peng Zhang, Tao You, Wei Huang, Yufei zha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-02T14:52:58Z","title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01226","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":"sha256:7398554ade85b28f46374581053eb651e44fb9eb9458f4ae3d859366bef09a23","target":"record","created_at":"2026-07-05T07:51:44Z","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":"79ce1ba28bfcdcb8a628b3adacd1f8ea867f1c628d73508f61d4add96d7e78d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-02T14:52:58Z","title_canon_sha256":"7b8224862376ca114bb7a77cc9ba96784230e8b5b2bc1e34f4446d45aa888eb4"},"schema_version":"1.0","source":{"id":"2403.01226","kind":"arxiv","version":1}},"canonical_sha256":"147d1fafc47f975fc3382f94ca446d7e30b1767b85df7d4629bcb1af96f289e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"147d1fafc47f975fc3382f94ca446d7e30b1767b85df7d4629bcb1af96f289e6","first_computed_at":"2026-07-05T07:51:44.102077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:44.102077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"If1xRaJrPQQltzcxeTGblfsnzHhPOGPSD2abPlhx9OEy9Wdfzunp0+woIjCLDccgjuuOUW57ZoGu3q4LkTOjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:44.102490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7398554ade85b28f46374581053eb651e44fb9eb9458f4ae3d859366bef09a23","sha256:fb32749cf3efad0e1bd629d6f6e83807dd1bbde6054c2b335b4b13d054198a9e"],"state_sha256":"ec11e9a3c611603c58941560217974249338092a45aa96e378bca0356057ffc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JBOlVqLpel3Rkb+08zqT4XjEF3u5juRQibYTOJQunn7PCKglIGiNOMvHsPi41qozNZusXlACBTGrDSD9IeMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:36:19.335750Z","bundle_sha256":"e01e438ad0936c8755e49fa73a3ecd15a80edb7d8a17638ad60f0755823a7847"}}