{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R4IDMNNSGZEZLG5NUPAW3757KW","short_pith_number":"pith:R4IDMNNS","canonical_record":{"source":{"id":"2407.10957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:54:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7555246fa7c6dad8a544f10ef2511dca785175aa04fa34d265d1b7d9132d6d62","abstract_canon_sha256":"b58d04267c80d6d2861191ccb27f22eb581697b0b7822867b58b6a1cb42be0ee"},"schema_version":"1.0"},"canonical_sha256":"8f103635b23649959bada3c16dffbf55aead2e5a2190e54164236760e4a5bf40","source":{"kind":"arxiv","id":"2407.10957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10957","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10957v1","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10957","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"R4IDMNNSGZEZ","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"R4IDMNNSGZEZLG5N","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"R4IDMNNS","created_at":"2026-07-05T08:44:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R4IDMNNSGZEZLG5NUPAW3757KW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:54:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7555246fa7c6dad8a544f10ef2511dca785175aa04fa34d265d1b7d9132d6d62","abstract_canon_sha256":"b58d04267c80d6d2861191ccb27f22eb581697b0b7822867b58b6a1cb42be0ee"},"schema_version":"1.0"},"canonical_sha256":"8f103635b23649959bada3c16dffbf55aead2e5a2190e54164236760e4a5bf40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:06.968399Z","signature_b64":"ZDBzTbuacq9ROTpLK5vhpikDA+BuCFKlEofDzWN0mwIbZbqA//s0TNJg6vNOqebFPByMclnzUJuOwFwxRApGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f103635b23649959bada3c16dffbf55aead2e5a2190e54164236760e4a5bf40","last_reissued_at":"2026-07-05T08:44:06.967953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:06.967953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10957","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":"2026-07-05T08:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJe0FHCho/6NgUZgGcF6bJEWx/Pu3ydV/0rDmr19m6l0lW5JiwggLGuGh99qR6p5sHHHWJtOyF8tXzl9QUVBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:47:32.155902Z"},"content_sha256":"b09f39d686bf122c7ff954c34252fc2ad0b756063e9fc589419e96ef36915264","schema_version":"1.0","event_id":"sha256:b09f39d686bf122c7ff954c34252fc2ad0b756063e9fc589419e96ef36915264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R4IDMNNSGZEZLG5NUPAW3757KW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Hu, Dongzhan Zhou, Guangyao Li, Honggang Zhang, Peiwen Sun, Yaoting Wang","submitted_at":"2024-07-15T17:54:45Z","abstract_excerpt":"Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. Such expressions are articulated in natural language forms but are enriched with multimodal cues, including audio and visual descriptions. To facilitate this research, we construct the first Ref-AVS benchmark, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10957","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/2407.10957/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":"2026-07-05T08:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FafTor+t+Wo/3ccd1pk0J94yD5rs/i6Ky9E2CQaI6x6ilcalCjA9s1dq1jl7PdOAedOesGep8NMpjeWPrld0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:47:32.156440Z"},"content_sha256":"dab31771e53d0ff3a1930c8fc06b0cc62917e926e255327d22b1148c48913cd7","schema_version":"1.0","event_id":"sha256:dab31771e53d0ff3a1930c8fc06b0cc62917e926e255327d22b1148c48913cd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4IDMNNSGZEZLG5NUPAW3757KW/bundle.json","state_url":"https://pith.science/pith/R4IDMNNSGZEZLG5NUPAW3757KW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4IDMNNSGZEZLG5NUPAW3757KW/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":"2026-08-10T18:47:32Z","links":{"resolver":"https://pith.science/pith/R4IDMNNSGZEZLG5NUPAW3757KW","bundle":"https://pith.science/pith/R4IDMNNSGZEZLG5NUPAW3757KW/bundle.json","state":"https://pith.science/pith/R4IDMNNSGZEZLG5NUPAW3757KW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4IDMNNSGZEZLG5NUPAW3757KW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R4IDMNNSGZEZLG5NUPAW3757KW","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":"b58d04267c80d6d2861191ccb27f22eb581697b0b7822867b58b6a1cb42be0ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:54:45Z","title_canon_sha256":"7555246fa7c6dad8a544f10ef2511dca785175aa04fa34d265d1b7d9132d6d62"},"schema_version":"1.0","source":{"id":"2407.10957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10957","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10957v1","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10957","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"R4IDMNNSGZEZ","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"R4IDMNNSGZEZLG5N","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"R4IDMNNS","created_at":"2026-07-05T08:44:06Z"}],"graph_snapshots":[{"event_id":"sha256:dab31771e53d0ff3a1930c8fc06b0cc62917e926e255327d22b1148c48913cd7","target":"graph","created_at":"2026-07-05T08:44:06Z","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/2407.10957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. Such expressions are articulated in natural language forms but are enriched with multimodal cues, including audio and visual descriptions. To facilitate this research, we construct the first Ref-AVS benchmark, which ","authors_text":"Di Hu, Dongzhan Zhou, Guangyao Li, Honggang Zhang, Peiwen Sun, Yaoting Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:54:45Z","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10957","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:b09f39d686bf122c7ff954c34252fc2ad0b756063e9fc589419e96ef36915264","target":"record","created_at":"2026-07-05T08:44:06Z","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":"b58d04267c80d6d2861191ccb27f22eb581697b0b7822867b58b6a1cb42be0ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:54:45Z","title_canon_sha256":"7555246fa7c6dad8a544f10ef2511dca785175aa04fa34d265d1b7d9132d6d62"},"schema_version":"1.0","source":{"id":"2407.10957","kind":"arxiv","version":1}},"canonical_sha256":"8f103635b23649959bada3c16dffbf55aead2e5a2190e54164236760e4a5bf40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f103635b23649959bada3c16dffbf55aead2e5a2190e54164236760e4a5bf40","first_computed_at":"2026-07-05T08:44:06.967953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:06.967953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZDBzTbuacq9ROTpLK5vhpikDA+BuCFKlEofDzWN0mwIbZbqA//s0TNJg6vNOqebFPByMclnzUJuOwFwxRApGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:06.968399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b09f39d686bf122c7ff954c34252fc2ad0b756063e9fc589419e96ef36915264","sha256:dab31771e53d0ff3a1930c8fc06b0cc62917e926e255327d22b1148c48913cd7"],"state_sha256":"d6b4140c44a641e3a18351a36d131e50e1f093c0b36242002e12b27344af6ae0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvdqyyazSXYY84AG/Dm8PKF5SF04w7D3n64mvFDSuiihwQUHlQRRHZdwEEtKLerl5JVeZntyqNAPWjXMrvVKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:47:32.161921Z","bundle_sha256":"4c4feed52ab762648f0760946470db21ad7e2a2579a1ca935b814443bc30020f"}}