{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GFOYPZZ7ZVODWWHAA4KNQE3Q2H","short_pith_number":"pith:GFOYPZZ7","canonical_record":{"source":{"id":"2310.18709","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"e809b201627c2f3d376ec6ba8d0b14443f1cca813983ddc7679d53f7673da825","abstract_canon_sha256":"a98bb8f8f358c0f064b01a7c3f555eeb34303be085e7f37fb2f4febc6b15bd74"},"schema_version":"1.0"},"canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","source":{"kind":"arxiv","id":"2310.18709","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18709","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18709v4","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18709","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"GFOYPZZ7ZVOD","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"GFOYPZZ7ZVODWWHA","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"GFOYPZZ7","created_at":"2026-07-05T10:21:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GFOYPZZ7ZVODWWHAA4KNQE3Q2H","target":"record","payload":{"canonical_record":{"source":{"id":"2310.18709","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"e809b201627c2f3d376ec6ba8d0b14443f1cca813983ddc7679d53f7673da825","abstract_canon_sha256":"a98bb8f8f358c0f064b01a7c3f555eeb34303be085e7f37fb2f4febc6b15bd74"},"schema_version":"1.0"},"canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:56.480533Z","signature_b64":"x83KgbMZTAV9BSqK1SYLkXNUeP61mz3APsTuDruYVwqYm4sSOOXRJ0dbSxzbwPzwf6cqUK3/ZCDhUK6sYVYiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","last_reissued_at":"2026-07-05T10:21:56.480097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:56.480097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.18709","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/ekl8GzXdzQuqJXd6Bwb4JKrlMNCOSSqAHHSKTBYZH2XCQCk8Ct4g9JCbhgMubpQEi7U4nk8ZojBRUb9zp0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:38:56.560038Z"},"content_sha256":"4e277422ef3d5ff9506b3262ccda6ce9eaaf02920e228794eee1590684d05bf7","schema_version":"1.0","event_id":"sha256:4e277422ef3d5ff9506b3262ccda6ce9eaaf02920e228794eee1590684d05bf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GFOYPZZ7ZVODWWHAA4KNQE3Q2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bowei Xing, Buwen Liang, Dantong Niu, Guangyao Li, Jinxing Zhou, Ji Shi, Liao Qu, Peiliang Zhang, Qixun Wang, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi, Yaru Chen","submitted_at":"2023-10-28T13:37:52Z","abstract_excerpt":"In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18709","kind":"arxiv","version":4},"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/2310.18709/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":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWpId99ivkMCa/uGEnvHgyTj+9jFbNBLYsJHPF09YgZs2X31qrKpebW2yYxZAabJqi0qzKLCLJNGtvDOsMgFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:38:56.560563Z"},"content_sha256":"8bac797e9ba1a1b2b6122680f250b6630c2ab7e2831b4a6d37b1907f9c260be1","schema_version":"1.0","event_id":"sha256:8bac797e9ba1a1b2b6122680f250b6630c2ab7e2831b4a6d37b1907f9c260be1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/bundle.json","state_url":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/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":"2026-08-11T04:38:56Z","links":{"resolver":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H","bundle":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/bundle.json","state":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GFOYPZZ7ZVODWWHAA4KNQE3Q2H","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":"a98bb8f8f358c0f064b01a7c3f555eeb34303be085e7f37fb2f4febc6b15bd74","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","title_canon_sha256":"e809b201627c2f3d376ec6ba8d0b14443f1cca813983ddc7679d53f7673da825"},"schema_version":"1.0","source":{"id":"2310.18709","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18709","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18709v4","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18709","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"GFOYPZZ7ZVOD","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"GFOYPZZ7ZVODWWHA","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"GFOYPZZ7","created_at":"2026-07-05T10:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:8bac797e9ba1a1b2b6122680f250b6630c2ab7e2831b4a6d37b1907f9c260be1","target":"graph","created_at":"2026-07-05T10:21:56Z","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/2310.18709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual de","authors_text":"Bowei Xing, Buwen Liang, Dantong Niu, Guangyao Li, Jinxing Zhou, Ji Shi, Liao Qu, Peiliang Zhang, Qixun Wang, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi, Yaru Chen","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","title":"Audio-Visual Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18709","kind":"arxiv","version":4},"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":"sha256:4e277422ef3d5ff9506b3262ccda6ce9eaaf02920e228794eee1590684d05bf7","target":"record","created_at":"2026-07-05T10:21:56Z","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":"a98bb8f8f358c0f064b01a7c3f555eeb34303be085e7f37fb2f4febc6b15bd74","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","title_canon_sha256":"e809b201627c2f3d376ec6ba8d0b14443f1cca813983ddc7679d53f7673da825"},"schema_version":"1.0","source":{"id":"2310.18709","kind":"arxiv","version":4}},"canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","first_computed_at":"2026-07-05T10:21:56.480097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:56.480097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x83KgbMZTAV9BSqK1SYLkXNUeP61mz3APsTuDruYVwqYm4sSOOXRJ0dbSxzbwPzwf6cqUK3/ZCDhUK6sYVYiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:56.480533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18709","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e277422ef3d5ff9506b3262ccda6ce9eaaf02920e228794eee1590684d05bf7","sha256:8bac797e9ba1a1b2b6122680f250b6630c2ab7e2831b4a6d37b1907f9c260be1"],"state_sha256":"c0177cc777c0a701dcdfa03faa80ff61f26e64834a511b1e7aed22755f9fe532"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HBxVN98cnjbLM30asVJt85bDx0h43+c32fELFY7mmTuVgKf/CRCWvJ4OYkJjO1FLmBbO9h1AQSKy2NZvsL0MAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:38:56.566046Z","bundle_sha256":"4c6c58330b036223880f5bee40c991680218851dc73b6d76e1b9e1dc5f307071"}}