{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PWXGWULKWZ26ZJAZC5EIYPDRFN","short_pith_number":"pith:PWXGWULK","canonical_record":{"source":{"id":"2310.07517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T14:15:25Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bff79116d9ad782d6de21a1ceb2f01e9f960a18529cb1ec72d7ef8cc54cb6e27","abstract_canon_sha256":"53906d3fadf88ebbe2256141ef881c4a0f30689ccdd89d1735fac206749d4d52"},"schema_version":"1.0"},"canonical_sha256":"7dae6b516ab675eca41917488c3c712b401eae5e1e4d1114a8946a604d25b8df","source":{"kind":"arxiv","id":"2310.07517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07517","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07517v1","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07517","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_12","alias_value":"PWXGWULKWZ26","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_16","alias_value":"PWXGWULKWZ26ZJAZ","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_8","alias_value":"PWXGWULK","created_at":"2026-07-05T06:59:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PWXGWULKWZ26ZJAZC5EIYPDRFN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T14:15:25Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bff79116d9ad782d6de21a1ceb2f01e9f960a18529cb1ec72d7ef8cc54cb6e27","abstract_canon_sha256":"53906d3fadf88ebbe2256141ef881c4a0f30689ccdd89d1735fac206749d4d52"},"schema_version":"1.0"},"canonical_sha256":"7dae6b516ab675eca41917488c3c712b401eae5e1e4d1114a8946a604d25b8df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:46.746997Z","signature_b64":"+dUuIOU/e/qglVMm0QvUPg1gvQuD9V8DGkNOfcLRxg2wYJwPYaPktba5M5mUIDSkRWxcobdrCEh8mcAlvxUFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dae6b516ab675eca41917488c3c712b401eae5e1e4d1114a8946a604d25b8df","last_reissued_at":"2026-07-05T06:59:46.746491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:46.746491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07517","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":"2026-07-05T06:59:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tB8acxlldOk3ylF3vhil4btNEs8xJzgW8Txv6md0lZN6Sb3eaur7V/HvhPTMMO4arq4NcCIlyrYmKzn3FOSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:05:36.069186Z"},"content_sha256":"7740a7c887ebc5e12b1d2fe498b52668955e2163bf177baf48c3768e7cc5efcc","schema_version":"1.0","event_id":"sha256:7740a7c887ebc5e12b1d2fe498b52668955e2163bf177baf48c3768e7cc5efcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PWXGWULKWZ26ZJAZC5EIYPDRFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Guangyao Li, Peipei Wu, Ruohao Guo, Wenwu Wang, Xubo Liu, Yaru Chen, Zhenbo Li","submitted_at":"2023-10-11T14:15:25Z","abstract_excerpt":"Audio-visual video parsing is the task of categorizing a video at the segment level with weak labels, and predicting them as audible or visible events. Recent methods for this task leverage the attention mechanism to capture the semantic correlations among the whole video across the audio-visual modalities. However, these approaches have overlooked the importance of individual segments within a video and the relationship among them, and tend to rely on a single modality when learning features. In this paper, we propose a novel interactive-enhanced cross-modal perception method~(CM-PIE), which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07517","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/2310.07517/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":"2026-07-05T06:59:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piqKifgiLHDW46Edy3eozc4X1GwxazhDiHmHP/HCT/e8uOyDpjyXeLsyz8vUf77ewBgqpHyO8A4LjBTb4ClNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:05:36.070159Z"},"content_sha256":"429a27143ec53886f3a00c503b27ebdf55020e32f14685b080f948818d3f45ea","schema_version":"1.0","event_id":"sha256:429a27143ec53886f3a00c503b27ebdf55020e32f14685b080f948818d3f45ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/bundle.json","state_url":"https://pith.science/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/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":"2026-08-16T23:05:36Z","links":{"resolver":"https://pith.science/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN","bundle":"https://pith.science/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/bundle.json","state":"https://pith.science/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWXGWULKWZ26ZJAZC5EIYPDRFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PWXGWULKWZ26ZJAZC5EIYPDRFN","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":"53906d3fadf88ebbe2256141ef881c4a0f30689ccdd89d1735fac206749d4d52","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T14:15:25Z","title_canon_sha256":"bff79116d9ad782d6de21a1ceb2f01e9f960a18529cb1ec72d7ef8cc54cb6e27"},"schema_version":"1.0","source":{"id":"2310.07517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07517","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07517v1","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07517","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_12","alias_value":"PWXGWULKWZ26","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_16","alias_value":"PWXGWULKWZ26ZJAZ","created_at":"2026-07-05T06:59:46Z"},{"alias_kind":"pith_short_8","alias_value":"PWXGWULK","created_at":"2026-07-05T06:59:46Z"}],"graph_snapshots":[{"event_id":"sha256:429a27143ec53886f3a00c503b27ebdf55020e32f14685b080f948818d3f45ea","target":"graph","created_at":"2026-07-05T06:59:46Z","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/2310.07517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual video parsing is the task of categorizing a video at the segment level with weak labels, and predicting them as audible or visible events. Recent methods for this task leverage the attention mechanism to capture the semantic correlations among the whole video across the audio-visual modalities. However, these approaches have overlooked the importance of individual segments within a video and the relationship among them, and tend to rely on a single modality when learning features. In this paper, we propose a novel interactive-enhanced cross-modal perception method~(CM-PIE), which ","authors_text":"Guangyao Li, Peipei Wu, Ruohao Guo, Wenwu Wang, Xubo Liu, Yaru Chen, Zhenbo Li","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T14:15:25Z","title":"CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07517","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":"sha256:7740a7c887ebc5e12b1d2fe498b52668955e2163bf177baf48c3768e7cc5efcc","target":"record","created_at":"2026-07-05T06:59:46Z","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":"53906d3fadf88ebbe2256141ef881c4a0f30689ccdd89d1735fac206749d4d52","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T14:15:25Z","title_canon_sha256":"bff79116d9ad782d6de21a1ceb2f01e9f960a18529cb1ec72d7ef8cc54cb6e27"},"schema_version":"1.0","source":{"id":"2310.07517","kind":"arxiv","version":1}},"canonical_sha256":"7dae6b516ab675eca41917488c3c712b401eae5e1e4d1114a8946a604d25b8df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dae6b516ab675eca41917488c3c712b401eae5e1e4d1114a8946a604d25b8df","first_computed_at":"2026-07-05T06:59:46.746491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:46.746491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+dUuIOU/e/qglVMm0QvUPg1gvQuD9V8DGkNOfcLRxg2wYJwPYaPktba5M5mUIDSkRWxcobdrCEh8mcAlvxUFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:46.746997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7740a7c887ebc5e12b1d2fe498b52668955e2163bf177baf48c3768e7cc5efcc","sha256:429a27143ec53886f3a00c503b27ebdf55020e32f14685b080f948818d3f45ea"],"state_sha256":"3950bd9fc096afaefe92121ac276d9dc5a659b5bef88be077fad128cadfb6873"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HY9bUWq6A+vfg9jE83zTA4wiYqtNWfgNL+d8FlR0gkqwRDaIjD6hzIrMk2+obKhj/AxJg+FqboBJfMcq0Kn4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:05:36.076716Z","bundle_sha256":"8bb3db1d8d5d716e3742352a93b046af58039f756f8233ad97d91d9453f465f0"}}