{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MJ2VF32QVAI42RZ6RRBY6CXFE5","short_pith_number":"pith:MJ2VF32Q","canonical_record":{"source":{"id":"2305.03907","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T02:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"ae2e7a250797193b0db5f72ee3facce56a252c7becf217b7befb4c16795eb8ec","abstract_canon_sha256":"a9b874610cd14e2cf681796f36f1d1d599ff7608ae069e8b04d12ce4d7bfa2f8"},"schema_version":"1.0"},"canonical_sha256":"627552ef50a811cd473e8c438f0ae527610c4807145bd7471b5d19ddef71acd1","source":{"kind":"arxiv","id":"2305.03907","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03907","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03907v3","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03907","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"MJ2VF32QVAI4","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"MJ2VF32QVAI42RZ6","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"MJ2VF32Q","created_at":"2026-07-05T07:59:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MJ2VF32QVAI42RZ6RRBY6CXFE5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03907","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T02:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"ae2e7a250797193b0db5f72ee3facce56a252c7becf217b7befb4c16795eb8ec","abstract_canon_sha256":"a9b874610cd14e2cf681796f36f1d1d599ff7608ae069e8b04d12ce4d7bfa2f8"},"schema_version":"1.0"},"canonical_sha256":"627552ef50a811cd473e8c438f0ae527610c4807145bd7471b5d19ddef71acd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:14.968075Z","signature_b64":"gi8inIH5b4CMuq4YvfEUAXAz+F7KNeNWhwpA7O5Kd2dIy8Ros1vxGVDEl4ebofu6cFvloaAScWZWirja0IpFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"627552ef50a811cd473e8c438f0ae527610c4807145bd7471b5d19ddef71acd1","last_reissued_at":"2026-07-05T07:59:14.967539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:14.967539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03907","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":"2026-07-05T07:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"115WJwqQq1oQZ1Zq0OXkXZQwgBMJaGmV6Sdr5XY2/NApw8whYa2jAqaDmD4t0LwI6RR3rGZjk45e4XgsMd+UDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:08:25.476362Z"},"content_sha256":"4e4bd758e44cc30fff91f72a7ed4dc8759c3f5298d9776f2eeafec925ff6ba1e","schema_version":"1.0","event_id":"sha256:4e4bd758e44cc30fff91f72a7ed4dc8759c3f5298d9776f2eeafec925ff6ba1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MJ2VF32QVAI42RZ6RRBY6CXFE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolin Lai, Fiona Ryan, James M. Rehg, Miao Liu, Wenqi Jia","submitted_at":"2023-05-06T02:53:13Z","abstract_excerpt":"Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we introduce the first model that leverages both the video and audio modalities for egocentric gaze anticipation. Specifically, we propose a Contrastive Spatial-Temporal Separable (CSTS) fusion approach that adopts two modules to separately capture audio-visual correlations in spatial and temporal dimensions, and applies a contrastive loss on the re-weighted au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03907","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/2305.03907/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":"2026-07-05T07:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75bJRvQLqGHXSgyM12rq9kzaSchIl+Uq27UrZ6YD49U/GuFa8oML9wsfAP6nprLTFvwWkSx+VSHlmzaMvz0jAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:08:25.477844Z"},"content_sha256":"b928927a304297268e20faa92433cba80be1a3cdc7965f38ba44ac84b5e16da9","schema_version":"1.0","event_id":"sha256:b928927a304297268e20faa92433cba80be1a3cdc7965f38ba44ac84b5e16da9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/bundle.json","state_url":"https://pith.science/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/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":"2026-08-07T04:08:25Z","links":{"resolver":"https://pith.science/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5","bundle":"https://pith.science/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/bundle.json","state":"https://pith.science/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJ2VF32QVAI42RZ6RRBY6CXFE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MJ2VF32QVAI42RZ6RRBY6CXFE5","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":"a9b874610cd14e2cf681796f36f1d1d599ff7608ae069e8b04d12ce4d7bfa2f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T02:53:13Z","title_canon_sha256":"ae2e7a250797193b0db5f72ee3facce56a252c7becf217b7befb4c16795eb8ec"},"schema_version":"1.0","source":{"id":"2305.03907","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03907","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03907v3","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03907","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"MJ2VF32QVAI4","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"MJ2VF32QVAI42RZ6","created_at":"2026-07-05T07:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"MJ2VF32Q","created_at":"2026-07-05T07:59:14Z"}],"graph_snapshots":[{"event_id":"sha256:b928927a304297268e20faa92433cba80be1a3cdc7965f38ba44ac84b5e16da9","target":"graph","created_at":"2026-07-05T07:59:14Z","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/2305.03907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we introduce the first model that leverages both the video and audio modalities for egocentric gaze anticipation. Specifically, we propose a Contrastive Spatial-Temporal Separable (CSTS) fusion approach that adopts two modules to separately capture audio-visual correlations in spatial and temporal dimensions, and applies a contrastive loss on the re-weighted au","authors_text":"Bolin Lai, Fiona Ryan, James M. Rehg, Miao Liu, Wenqi Jia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T02:53:13Z","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03907","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":"sha256:4e4bd758e44cc30fff91f72a7ed4dc8759c3f5298d9776f2eeafec925ff6ba1e","target":"record","created_at":"2026-07-05T07:59:14Z","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":"a9b874610cd14e2cf681796f36f1d1d599ff7608ae069e8b04d12ce4d7bfa2f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T02:53:13Z","title_canon_sha256":"ae2e7a250797193b0db5f72ee3facce56a252c7becf217b7befb4c16795eb8ec"},"schema_version":"1.0","source":{"id":"2305.03907","kind":"arxiv","version":3}},"canonical_sha256":"627552ef50a811cd473e8c438f0ae527610c4807145bd7471b5d19ddef71acd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"627552ef50a811cd473e8c438f0ae527610c4807145bd7471b5d19ddef71acd1","first_computed_at":"2026-07-05T07:59:14.967539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:14.967539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gi8inIH5b4CMuq4YvfEUAXAz+F7KNeNWhwpA7O5Kd2dIy8Ros1vxGVDEl4ebofu6cFvloaAScWZWirja0IpFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:14.968075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03907","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e4bd758e44cc30fff91f72a7ed4dc8759c3f5298d9776f2eeafec925ff6ba1e","sha256:b928927a304297268e20faa92433cba80be1a3cdc7965f38ba44ac84b5e16da9"],"state_sha256":"82e9db74a87ce4d77443bb4b53270453ae77d5312587bb243ca1ea0d41e7c33b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fj8bRTSB3aHZBaM/ZkctNoJXF0KCOcuva5c6wmNbndEe3LsMLQFCqjLJHcUnIKQdDkXP6Cit/e9hBBDp5msGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:08:25.491514Z","bundle_sha256":"8e24b1a43f0653ce93afe2394eec5993c22160498149c26f8f48fc912e9df90c"}}