{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C2R6ET4CC3WXYBHHSBBDYYLZ2X","short_pith_number":"pith:C2R6ET4C","canonical_record":{"source":{"id":"2407.21721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-31T16:14:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f55026eaea4de30602d057ecc52fbf6562f59c5841b47b826427f16eb966ece","abstract_canon_sha256":"ea72c4fce9de43ea7ff6de54ff193670d56a1d050edb64d8727ebbb595e7818a"},"schema_version":"1.0"},"canonical_sha256":"16a3e24f8216ed7c04e790423c6179d5ffed819bff6d44dbc5689fcd8aee71fe","source":{"kind":"arxiv","id":"2407.21721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21721","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21721v1","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21721","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"C2R6ET4CC3WX","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"C2R6ET4CC3WXYBHH","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"C2R6ET4C","created_at":"2026-07-05T08:50:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C2R6ET4CC3WXYBHHSBBDYYLZ2X","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-31T16:14:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f55026eaea4de30602d057ecc52fbf6562f59c5841b47b826427f16eb966ece","abstract_canon_sha256":"ea72c4fce9de43ea7ff6de54ff193670d56a1d050edb64d8727ebbb595e7818a"},"schema_version":"1.0"},"canonical_sha256":"16a3e24f8216ed7c04e790423c6179d5ffed819bff6d44dbc5689fcd8aee71fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:42.829241Z","signature_b64":"3wdtyw67stAybvjOviEN4Pbak7vjj4DzfImWveRFVvWmKlO5GFP3kBsEZhe7SAwoSfcvfhZ5sgq11yUmeCkKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a3e24f8216ed7c04e790423c6179d5ffed819bff6d44dbc5689fcd8aee71fe","last_reissued_at":"2026-07-05T08:50:42.828763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:42.828763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21721","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":"2026-07-05T08:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gahQ6duAPzErfPCihWycc9ZSDURm08topH2jSnRIyLfFH+tLFYHf/XoP1BRgjKnpit+WNC8lmmkmZDEuTCxJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:28:13.561018Z"},"content_sha256":"b6eb4423e1eebc239f53d00df73edf47280aa809edc906c0677f295851359ba5","schema_version":"1.0","event_id":"sha256:b6eb4423e1eebc239f53d00df73edf47280aa809edc906c0677f295851359ba5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C2R6ET4CC3WXYBHHSBBDYYLZ2X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Vocabulary Audio-Visual Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MM","authors_text":"Bowei Xing, Dantong Niu, Ji Shi, Liao Qu, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi","submitted_at":"2024-07-31T16:14:09Z","abstract_excerpt":"Audio-visual semantic segmentation (AVSS) aims to segment and classify sounding objects in videos with acoustic cues. However, most approaches operate on the close-set assumption and only identify pre-defined categories from training data, lacking the generalization ability to detect novel categories in practical applications. In this paper, we introduce a new task: open-vocabulary audio-visual semantic segmentation, extending AVSS task to open-world scenarios beyond the annotated label space. This is a more challenging task that requires recognizing all categories, even those that have never "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21721","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/2407.21721/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":"2026-07-05T08:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5Zyz1QEjRjwZeCPVucUcps1PM8G3Ko6Y/vZ3d3D3TUqYAL8PG02PoSB3e9KnDH0QHvudnCyuvH8G9ZJvIWeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:28:13.561418Z"},"content_sha256":"4b0c4d2fb2351d1dd5cf4924639a80521ab1805f507e47014f2b8e0580c53a6f","schema_version":"1.0","event_id":"sha256:4b0c4d2fb2351d1dd5cf4924639a80521ab1805f507e47014f2b8e0580c53a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/bundle.json","state_url":"https://pith.science/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/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":"2026-07-17T07:28:13Z","links":{"resolver":"https://pith.science/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X","bundle":"https://pith.science/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/bundle.json","state":"https://pith.science/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2R6ET4CC3WXYBHHSBBDYYLZ2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C2R6ET4CC3WXYBHHSBBDYYLZ2X","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":"ea72c4fce9de43ea7ff6de54ff193670d56a1d050edb64d8727ebbb595e7818a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-31T16:14:09Z","title_canon_sha256":"6f55026eaea4de30602d057ecc52fbf6562f59c5841b47b826427f16eb966ece"},"schema_version":"1.0","source":{"id":"2407.21721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21721","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21721v1","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21721","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"C2R6ET4CC3WX","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"C2R6ET4CC3WXYBHH","created_at":"2026-07-05T08:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"C2R6ET4C","created_at":"2026-07-05T08:50:42Z"}],"graph_snapshots":[{"event_id":"sha256:4b0c4d2fb2351d1dd5cf4924639a80521ab1805f507e47014f2b8e0580c53a6f","target":"graph","created_at":"2026-07-05T08:50:42Z","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/2407.21721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual semantic segmentation (AVSS) aims to segment and classify sounding objects in videos with acoustic cues. However, most approaches operate on the close-set assumption and only identify pre-defined categories from training data, lacking the generalization ability to detect novel categories in practical applications. In this paper, we introduce a new task: open-vocabulary audio-visual semantic segmentation, extending AVSS task to open-world scenarios beyond the annotated label space. This is a more challenging task that requires recognizing all categories, even those that have never ","authors_text":"Bowei Xing, Dantong Niu, Ji Shi, Liao Qu, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-31T16:14:09Z","title":"Open-Vocabulary Audio-Visual Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21721","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:b6eb4423e1eebc239f53d00df73edf47280aa809edc906c0677f295851359ba5","target":"record","created_at":"2026-07-05T08:50:42Z","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":"ea72c4fce9de43ea7ff6de54ff193670d56a1d050edb64d8727ebbb595e7818a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-31T16:14:09Z","title_canon_sha256":"6f55026eaea4de30602d057ecc52fbf6562f59c5841b47b826427f16eb966ece"},"schema_version":"1.0","source":{"id":"2407.21721","kind":"arxiv","version":1}},"canonical_sha256":"16a3e24f8216ed7c04e790423c6179d5ffed819bff6d44dbc5689fcd8aee71fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16a3e24f8216ed7c04e790423c6179d5ffed819bff6d44dbc5689fcd8aee71fe","first_computed_at":"2026-07-05T08:50:42.828763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:42.828763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wdtyw67stAybvjOviEN4Pbak7vjj4DzfImWveRFVvWmKlO5GFP3kBsEZhe7SAwoSfcvfhZ5sgq11yUmeCkKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:42.829241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6eb4423e1eebc239f53d00df73edf47280aa809edc906c0677f295851359ba5","sha256:4b0c4d2fb2351d1dd5cf4924639a80521ab1805f507e47014f2b8e0580c53a6f"],"state_sha256":"29cca78035747fa8f355c9c11f74d92da79438f4539c4f0376f7fdcb4c9b08d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EUOuerrJdG628NCztt38dJyqHe08CaBEGsEt+9yNHCiXi9uHa3ggJd3lLnecxy0N/3R02BJ0E5f8ZCYRnlUZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:28:13.563601Z","bundle_sha256":"525f676e9c15e7d67163378cd1c6a1c7d3b017cd8adb545aec0da7ea00c7f35b"}}