{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MOHONXRAKDADPZBQ6VUAEZJHZU","short_pith_number":"pith:MOHONXRA","canonical_record":{"source":{"id":"2303.13471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:43:11Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"77ae45d0a8f5bae513fbbda46a318f5a88949b5dc314f7101964afd52e79273a","abstract_canon_sha256":"e57a244691cd0818ec7b44a47ff7fd0d5285375b45ebda8bcbad4f8b23b5149b"},"schema_version":"1.0"},"canonical_sha256":"638ee6de2050c037e430f568026527cd2a3f31c95caeb5da337e18f7aae872b0","source":{"kind":"arxiv","id":"2303.13471","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13471","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13471v1","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13471","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"MOHONXRAKDAD","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"MOHONXRAKDADPZBQ","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"MOHONXRA","created_at":"2026-07-05T05:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MOHONXRAKDADPZBQ6VUAEZJHZU","target":"record","payload":{"canonical_record":{"source":{"id":"2303.13471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:43:11Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"77ae45d0a8f5bae513fbbda46a318f5a88949b5dc314f7101964afd52e79273a","abstract_canon_sha256":"e57a244691cd0818ec7b44a47ff7fd0d5285375b45ebda8bcbad4f8b23b5149b"},"schema_version":"1.0"},"canonical_sha256":"638ee6de2050c037e430f568026527cd2a3f31c95caeb5da337e18f7aae872b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:02.699747Z","signature_b64":"ZFbjgQ4NrqSEcvj3wzh4KXKxNyVYZhTzNtUQF9SnLh/QkWyDJKvi1Bb8S5Q/GDxQkYiFTotT2E3rVAejSQ9hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638ee6de2050c037e430f568026527cd2a3f31c95caeb5da337e18f7aae872b0","last_reissued_at":"2026-07-05T05:54:02.699301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:02.699301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.13471","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":"2026-07-05T05:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6/CNH232/6R4tF6TcYw/vcP+EiL6pxhAv657Ov+9UkykvV8uieHXut35PTLaiZO5cVK/ML76nHk2/4Ka4cdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:17:57.734298Z"},"content_sha256":"b26d7949d44f7f9971f9918ef095d8a307974d7b8e9ca2044007f8ae9230547b","schema_version":"1.0","event_id":"sha256:b26d7949d44f7f9971f9918ef095d8a307974d7b8e9ca2044007f8ae9230547b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MOHONXRAKDADPZBQ6VUAEZJHZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Egocentric Audio-Visual Object Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Yapeng Tian","submitted_at":"2023-03-23T17:43:11Z","abstract_excerpt":"Humans naturally perceive surrounding scenes by unifying sound and sight in a first-person view. Likewise, machines are advanced to approach human intelligence by learning with multisensory inputs from an egocentric perspective. In this paper, we explore the challenging egocentric audio-visual object localization task and observe that 1) egomotion commonly exists in first-person recordings, even within a short duration; 2) The out-of-view sound components can be created while wearers shift their attention. To address the first problem, we propose a geometry-aware temporal aggregation module to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13471","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/2303.13471/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":"2026-07-05T05:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JINUFiVvaaH+j7S1XQYVU7t1mGphAhZrOLQgwapp7kchiDO2WaNSPp33dRXrCBHMlLC0TWrGwSi562nnEPBnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:17:57.735423Z"},"content_sha256":"72dfdbd4c286df21300a0b012e07a72883ff8890eaa8486f30bd1b996d6b8700","schema_version":"1.0","event_id":"sha256:72dfdbd4c286df21300a0b012e07a72883ff8890eaa8486f30bd1b996d6b8700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/bundle.json","state_url":"https://pith.science/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/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":"2026-08-17T04:17:57Z","links":{"resolver":"https://pith.science/pith/MOHONXRAKDADPZBQ6VUAEZJHZU","bundle":"https://pith.science/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/bundle.json","state":"https://pith.science/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOHONXRAKDADPZBQ6VUAEZJHZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MOHONXRAKDADPZBQ6VUAEZJHZU","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":"e57a244691cd0818ec7b44a47ff7fd0d5285375b45ebda8bcbad4f8b23b5149b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:43:11Z","title_canon_sha256":"77ae45d0a8f5bae513fbbda46a318f5a88949b5dc314f7101964afd52e79273a"},"schema_version":"1.0","source":{"id":"2303.13471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13471","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13471v1","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13471","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"MOHONXRAKDAD","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"MOHONXRAKDADPZBQ","created_at":"2026-07-05T05:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"MOHONXRA","created_at":"2026-07-05T05:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:72dfdbd4c286df21300a0b012e07a72883ff8890eaa8486f30bd1b996d6b8700","target":"graph","created_at":"2026-07-05T05:54:02Z","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/2303.13471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans naturally perceive surrounding scenes by unifying sound and sight in a first-person view. Likewise, machines are advanced to approach human intelligence by learning with multisensory inputs from an egocentric perspective. In this paper, we explore the challenging egocentric audio-visual object localization task and observe that 1) egomotion commonly exists in first-person recordings, even within a short duration; 2) The out-of-view sound components can be created while wearers shift their attention. To address the first problem, we propose a geometry-aware temporal aggregation module to","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Yapeng Tian","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:43:11Z","title":"Egocentric Audio-Visual Object Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13471","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:b26d7949d44f7f9971f9918ef095d8a307974d7b8e9ca2044007f8ae9230547b","target":"record","created_at":"2026-07-05T05:54:02Z","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":"e57a244691cd0818ec7b44a47ff7fd0d5285375b45ebda8bcbad4f8b23b5149b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:43:11Z","title_canon_sha256":"77ae45d0a8f5bae513fbbda46a318f5a88949b5dc314f7101964afd52e79273a"},"schema_version":"1.0","source":{"id":"2303.13471","kind":"arxiv","version":1}},"canonical_sha256":"638ee6de2050c037e430f568026527cd2a3f31c95caeb5da337e18f7aae872b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"638ee6de2050c037e430f568026527cd2a3f31c95caeb5da337e18f7aae872b0","first_computed_at":"2026-07-05T05:54:02.699301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:02.699301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZFbjgQ4NrqSEcvj3wzh4KXKxNyVYZhTzNtUQF9SnLh/QkWyDJKvi1Bb8S5Q/GDxQkYiFTotT2E3rVAejSQ9hDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:02.699747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b26d7949d44f7f9971f9918ef095d8a307974d7b8e9ca2044007f8ae9230547b","sha256:72dfdbd4c286df21300a0b012e07a72883ff8890eaa8486f30bd1b996d6b8700"],"state_sha256":"a4a455445de30f25dfec32d56543f62718374672591890933e15920bc4c0e625"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oei2rLRDlzmYXlc+ZUCGAMM2sT5UXUN+a7LAgiRwmeeV0R0ug52LowRWsK/+q4idYyetCq38kyL9oRFyNtpRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:17:57.812021Z","bundle_sha256":"75b33db3003cdab2b68486f02884ce204741106a33b8fa2a0c15c33d49c37d4c"}}