{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V4DWITKUT475JYISISJC7RZ3XR","short_pith_number":"pith:V4DWITKU","canonical_record":{"source":{"id":"2504.14267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T11:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"a56d594c94969901c2b598cd74060037962cf191386770dd8d515a4ba834b500","abstract_canon_sha256":"de02f69c0db097acf0e51f0edfde8aa189e4badaa796866fe0fa7c3ca98827ba"},"schema_version":"1.0"},"canonical_sha256":"af07644d549f3fd4e11244922fc73bbc50fe9af1ea64ad643a8995c69fa8cb5c","source":{"kind":"arxiv","id":"2504.14267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14267","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14267v1","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14267","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"V4DWITKUT475","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"V4DWITKUT475JYIS","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"V4DWITKU","created_at":"2026-07-05T10:51:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V4DWITKUT475JYISISJC7RZ3XR","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T11:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"a56d594c94969901c2b598cd74060037962cf191386770dd8d515a4ba834b500","abstract_canon_sha256":"de02f69c0db097acf0e51f0edfde8aa189e4badaa796866fe0fa7c3ca98827ba"},"schema_version":"1.0"},"canonical_sha256":"af07644d549f3fd4e11244922fc73bbc50fe9af1ea64ad643a8995c69fa8cb5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:40.891626Z","signature_b64":"Oyq5jxDXt8VZe/ndax9+cRcyD68UkrRntU3YVoLpwLfAFsxi1/5fFyFfxBZ1JJRIo7Q4OZ6pvDhROiLPnBUoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af07644d549f3fd4e11244922fc73bbc50fe9af1ea64ad643a8995c69fa8cb5c","last_reissued_at":"2026-07-05T10:51:40.891116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:40.891116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14267","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":"2026-07-05T10:51:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AJPilblD2b9bEYAhQI2yOK5hizZxvPLz3A7wuJXDYGDNVMnfRe6SaxS0tFiOl/QmnSdfP1HT+UZ2o/AMN8EBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:40:06.179414Z"},"content_sha256":"9a563dca1b76d20fb78a70bb81e1a7559bb6028c5592dcd8fcab9317256390f7","schema_version":"1.0","event_id":"sha256:9a563dca1b76d20fb78a70bb81e1a7559bb6028c5592dcd8fcab9317256390f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V4DWITKUT475JYISISJC7RZ3XR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Yu, Moncef Gabbouj, Wei Zhou, Xuanzhe Sun","submitted_at":"2025-04-19T11:30:54Z","abstract_excerpt":"Video saliency prediction is crucial for downstream applications, such as video compression and human-computer interaction. With the flourishing of multimodal learning, researchers started to explore multimodal video saliency prediction, including audio-visual and text-visual approaches. Auditory cues guide the gaze of viewers to sound sources, while textual cues provide semantic guidance for understanding video content. Integrating these complementary cues can improve the accuracy of saliency prediction. Therefore, we attempt to simultaneously analyze visual, auditory, and textual modalities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14267","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/2504.14267/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":"2026-07-05T10:51:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0eWShhHJu391hErIcYzcPyGM2HPm30RqRzUPjNQM85E6q0PpXJ2AaCmJCCVXfC0JXdJwL9jQu8Xz0p80A+IkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:40:06.179786Z"},"content_sha256":"4fb1335ad55bed39019010437ab30d8abb606d17459e65c62d5fa5601e60090d","schema_version":"1.0","event_id":"sha256:4fb1335ad55bed39019010437ab30d8abb606d17459e65c62d5fa5601e60090d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4DWITKUT475JYISISJC7RZ3XR/bundle.json","state_url":"https://pith.science/pith/V4DWITKUT475JYISISJC7RZ3XR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4DWITKUT475JYISISJC7RZ3XR/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":"2026-07-06T08:40:06Z","links":{"resolver":"https://pith.science/pith/V4DWITKUT475JYISISJC7RZ3XR","bundle":"https://pith.science/pith/V4DWITKUT475JYISISJC7RZ3XR/bundle.json","state":"https://pith.science/pith/V4DWITKUT475JYISISJC7RZ3XR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4DWITKUT475JYISISJC7RZ3XR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V4DWITKUT475JYISISJC7RZ3XR","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":"de02f69c0db097acf0e51f0edfde8aa189e4badaa796866fe0fa7c3ca98827ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T11:30:54Z","title_canon_sha256":"a56d594c94969901c2b598cd74060037962cf191386770dd8d515a4ba834b500"},"schema_version":"1.0","source":{"id":"2504.14267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14267","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14267v1","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14267","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"V4DWITKUT475","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"V4DWITKUT475JYIS","created_at":"2026-07-05T10:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"V4DWITKU","created_at":"2026-07-05T10:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:4fb1335ad55bed39019010437ab30d8abb606d17459e65c62d5fa5601e60090d","target":"graph","created_at":"2026-07-05T10:51:40Z","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/2504.14267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video saliency prediction is crucial for downstream applications, such as video compression and human-computer interaction. With the flourishing of multimodal learning, researchers started to explore multimodal video saliency prediction, including audio-visual and text-visual approaches. Auditory cues guide the gaze of viewers to sound sources, while textual cues provide semantic guidance for understanding video content. Integrating these complementary cues can improve the accuracy of saliency prediction. Therefore, we attempt to simultaneously analyze visual, auditory, and textual modalities ","authors_text":"Li Yu, Moncef Gabbouj, Wei Zhou, Xuanzhe Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T11:30:54Z","title":"Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14267","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":"sha256:9a563dca1b76d20fb78a70bb81e1a7559bb6028c5592dcd8fcab9317256390f7","target":"record","created_at":"2026-07-05T10:51:40Z","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":"de02f69c0db097acf0e51f0edfde8aa189e4badaa796866fe0fa7c3ca98827ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T11:30:54Z","title_canon_sha256":"a56d594c94969901c2b598cd74060037962cf191386770dd8d515a4ba834b500"},"schema_version":"1.0","source":{"id":"2504.14267","kind":"arxiv","version":1}},"canonical_sha256":"af07644d549f3fd4e11244922fc73bbc50fe9af1ea64ad643a8995c69fa8cb5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af07644d549f3fd4e11244922fc73bbc50fe9af1ea64ad643a8995c69fa8cb5c","first_computed_at":"2026-07-05T10:51:40.891116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:40.891116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oyq5jxDXt8VZe/ndax9+cRcyD68UkrRntU3YVoLpwLfAFsxi1/5fFyFfxBZ1JJRIo7Q4OZ6pvDhROiLPnBUoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:40.891626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a563dca1b76d20fb78a70bb81e1a7559bb6028c5592dcd8fcab9317256390f7","sha256:4fb1335ad55bed39019010437ab30d8abb606d17459e65c62d5fa5601e60090d"],"state_sha256":"919d038edaf54e3178959d8c29929212c2e279646239ce3cf541d1f7f9e8979d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKS9BuuakegP5La2Ej6GKihFSQ0E0DEQ3khBTWOJoj6LJtTtzKF6b5LPrSQTnBD6XOnhT/hRlGgaNFRzPm0kCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:40:06.181874Z","bundle_sha256":"9a573fa42cd1aeb24295cebd4aee893abb2997491f7af5ab1fb913db2715a484"}}