{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ODETY2BBXVSOKQFZ4LULVQJHR7","short_pith_number":"pith:ODETY2BB","canonical_record":{"source":{"id":"2507.22886","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"46faef2cf9ca9849f4ddd54cb5d3e10345d2b6abbca0620bfa483f2256fb7cd1","abstract_canon_sha256":"6033c587072ba4c9119b9e104a23c31e3d544aa339eed7f7d9f9a9d4922c623f"},"schema_version":"1.0"},"canonical_sha256":"70c93c6821bd64e540b9e2e8bac1278fe9b5843a3da0b2423affd05404dfb61a","source":{"kind":"arxiv","id":"2507.22886","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22886","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22886v2","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22886","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"ODETY2BBXVSO","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"ODETY2BBXVSOKQFZ","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"ODETY2BB","created_at":"2026-07-05T11:46:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ODETY2BBXVSOKQFZ4LULVQJHR7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22886","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"46faef2cf9ca9849f4ddd54cb5d3e10345d2b6abbca0620bfa483f2256fb7cd1","abstract_canon_sha256":"6033c587072ba4c9119b9e104a23c31e3d544aa339eed7f7d9f9a9d4922c623f"},"schema_version":"1.0"},"canonical_sha256":"70c93c6821bd64e540b9e2e8bac1278fe9b5843a3da0b2423affd05404dfb61a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:00.802029Z","signature_b64":"x/Uis2v7u3H2fZWYHf8L1y30LklcIMhZH1eK7HXFVq6bmS7Wh7u0iKvcejhWaczZKvKS2p/Bru8uLIbG8KowBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c93c6821bd64e540b9e2e8bac1278fe9b5843a3da0b2423affd05404dfb61a","last_reissued_at":"2026-07-05T11:46:00.801528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:00.801528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22886","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3A4SCQsK6ZzBmtJfxN18Czz42gTMDnkCgodaVN59FZkBdlD7XR+sCgTojSXcdeZQ4LpjCDp3J5ccEQiQxlqjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:38:47.672958Z"},"content_sha256":"7eae21b31f66f8c7581efb2fa9e7a8824ddcfe91fa073384d6f51afdf13dd1dc","schema_version":"1.0","event_id":"sha256:7eae21b31f66f8c7581efb2fa9e7a8824ddcfe91fa073384d6f51afdf13dd1dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ODETY2BBXVSOKQFZ4LULVQJHR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangquan Jie, Henghui Ding, Kaining Ying, Yu-Gang Jiang","submitted_at":"2025-07-30T17:59:31Z","abstract_excerpt":"Referring audio-visual segmentation (RAVS) has recently seen significant advancements, yet challenges remain in integrating multimodal information and deeply understanding and reasoning about audiovisual content. To extend the boundaries of RAVS and facilitate future research in this field, we propose Omnimodal Referring Audio-Visual Segmentation (OmniAVS), a new dataset containing 2,104 videos and 61,095 multimodal referring expressions. OmniAVS stands out with three key innovations: (1) 8 types of multimodal expressions that flexibly combine text, speech, sound, and visual cues; (2) an empha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22886","kind":"arxiv","version":2},"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/2507.22886/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":"2026-07-05T11:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vo1HPoCZMjCSx7rQB1TkpE90p3J/pGfNh+ogLyzSF2BZF8B2vB5syfzYA7jJZmPHkm5TXgW2ijN6m7B+NDn4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:38:47.673339Z"},"content_sha256":"e9db1f7906923d357c23d84e386d48b26b3ce2fcf8495361fb43f0f65a57d94c","schema_version":"1.0","event_id":"sha256:e9db1f7906923d357c23d84e386d48b26b3ce2fcf8495361fb43f0f65a57d94c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/bundle.json","state_url":"https://pith.science/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/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":"2026-08-07T06:38:47Z","links":{"resolver":"https://pith.science/pith/ODETY2BBXVSOKQFZ4LULVQJHR7","bundle":"https://pith.science/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/bundle.json","state":"https://pith.science/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODETY2BBXVSOKQFZ4LULVQJHR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ODETY2BBXVSOKQFZ4LULVQJHR7","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":"6033c587072ba4c9119b9e104a23c31e3d544aa339eed7f7d9f9a9d4922c623f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:59:31Z","title_canon_sha256":"46faef2cf9ca9849f4ddd54cb5d3e10345d2b6abbca0620bfa483f2256fb7cd1"},"schema_version":"1.0","source":{"id":"2507.22886","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22886","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22886v2","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22886","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"ODETY2BBXVSO","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"ODETY2BBXVSOKQFZ","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"ODETY2BB","created_at":"2026-07-05T11:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:e9db1f7906923d357c23d84e386d48b26b3ce2fcf8495361fb43f0f65a57d94c","target":"graph","created_at":"2026-07-05T11:46:00Z","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/2507.22886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring audio-visual segmentation (RAVS) has recently seen significant advancements, yet challenges remain in integrating multimodal information and deeply understanding and reasoning about audiovisual content. To extend the boundaries of RAVS and facilitate future research in this field, we propose Omnimodal Referring Audio-Visual Segmentation (OmniAVS), a new dataset containing 2,104 videos and 61,095 multimodal referring expressions. OmniAVS stands out with three key innovations: (1) 8 types of multimodal expressions that flexibly combine text, speech, sound, and visual cues; (2) an empha","authors_text":"Guangquan Jie, Henghui Ding, Kaining Ying, Yu-Gang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:59:31Z","title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22886","kind":"arxiv","version":2},"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":"sha256:7eae21b31f66f8c7581efb2fa9e7a8824ddcfe91fa073384d6f51afdf13dd1dc","target":"record","created_at":"2026-07-05T11:46:00Z","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":"6033c587072ba4c9119b9e104a23c31e3d544aa339eed7f7d9f9a9d4922c623f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:59:31Z","title_canon_sha256":"46faef2cf9ca9849f4ddd54cb5d3e10345d2b6abbca0620bfa483f2256fb7cd1"},"schema_version":"1.0","source":{"id":"2507.22886","kind":"arxiv","version":2}},"canonical_sha256":"70c93c6821bd64e540b9e2e8bac1278fe9b5843a3da0b2423affd05404dfb61a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70c93c6821bd64e540b9e2e8bac1278fe9b5843a3da0b2423affd05404dfb61a","first_computed_at":"2026-07-05T11:46:00.801528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:00.801528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x/Uis2v7u3H2fZWYHf8L1y30LklcIMhZH1eK7HXFVq6bmS7Wh7u0iKvcejhWaczZKvKS2p/Bru8uLIbG8KowBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:00.802029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22886","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eae21b31f66f8c7581efb2fa9e7a8824ddcfe91fa073384d6f51afdf13dd1dc","sha256:e9db1f7906923d357c23d84e386d48b26b3ce2fcf8495361fb43f0f65a57d94c"],"state_sha256":"97e389bc23c14026659507829f7afca943dd549550df733154b4d4ec9504aded"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"foNGskzUa/VyPwEnKFT6SRXy9Tiuz56RbA7ACrNz5Yzc/xFbmraL7Aa69LCRowsyGo/NNuYL8omviSocQ+VlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:38:47.676082Z","bundle_sha256":"6c3b29366a21ae8411b859d8af2ba70caec129c39108b858d2981b9dfc409e46"}}