{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BFRS4AB62AACDBK7QXXPWZZPTU","short_pith_number":"pith:BFRS4AB6","canonical_record":{"source":{"id":"2408.01708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T08:25:26Z","cross_cats_sorted":[],"title_canon_sha256":"d2d063a2b1034aeb5cc961231b71ef9202b4d187bfd325557ce5eef29c091d62","abstract_canon_sha256":"ae5550531657839f9c742415fc77d7d1b6c49734694f23d98499773fbcd56d84"},"schema_version":"1.0"},"canonical_sha256":"09632e003ed00021855f85eefb672f9d1b12de3a0875e3f25e712d1a72bc71e7","source":{"kind":"arxiv","id":"2408.01708","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01708","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01708v1","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01708","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"BFRS4AB62AAC","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"BFRS4AB62AACDBK7","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"BFRS4AB6","created_at":"2026-07-05T08:52:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BFRS4AB62AACDBK7QXXPWZZPTU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T08:25:26Z","cross_cats_sorted":[],"title_canon_sha256":"d2d063a2b1034aeb5cc961231b71ef9202b4d187bfd325557ce5eef29c091d62","abstract_canon_sha256":"ae5550531657839f9c742415fc77d7d1b6c49734694f23d98499773fbcd56d84"},"schema_version":"1.0"},"canonical_sha256":"09632e003ed00021855f85eefb672f9d1b12de3a0875e3f25e712d1a72bc71e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:01.647046Z","signature_b64":"+ut5BTl0fuvBrXixkRmCnG/cwHBlueeLJRJbCoK4MoJrAx9qaBjSYGF0+RD82UwDEm8e/uX4Mhw7AR3upqh+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09632e003ed00021855f85eefb672f9d1b12de3a0875e3f25e712d1a72bc71e7","last_reissued_at":"2026-07-05T08:52:01.646646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:01.646646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01708","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":"2026-07-05T08:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvTELeY+3YM5Do0iOwPk9Fzw1enuvlQT6uFaGxxytAxyp3v+DaKjGEa7xYZIpWepxe89gnSI7Lqi3cXF9+MnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:33:20.035045Z"},"content_sha256":"6de54f1be024292954b6cc254898660633b06b56ca15b7ca01a731c55052d82a","schema_version":"1.0","event_id":"sha256:6de54f1be024292954b6cc254898660633b06b56ca15b7ca01a731c55052d82a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BFRS4AB62AACDBK7QXXPWZZPTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Li, Jiazhong Yu, Linsu Shi, Qinghua Liang, Qi Yang, Shiming Xiang, Zili Wang","submitted_at":"2024-08-03T08:25:26Z","abstract_excerpt":"Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the network, we identify two key obstacles in AVS models: 1) attention dissipation, corresponding to the over-concentrated attention weights by Softmax within restricted frames, and 2) inefficient, burdensome transformer decoder, caused by narrow focus patterns in early stages. In this paper, we introduce AVESFormer, the first real-time Audio-Visual Efficient S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01708","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/2408.01708/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":"2026-07-05T08:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfxJjQrXEQWBML48JinJvaMu8WUeS8hNbfRBfOYaqg4uGJsP5H/v7s6B8ycWvkv8cs+f14IxpcyvAC5AeqIUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:33:20.035537Z"},"content_sha256":"28ba87ee012f3b4e2edd8f08dccccac6c709e61072fcfad968f4bb8016bc272f","schema_version":"1.0","event_id":"sha256:28ba87ee012f3b4e2edd8f08dccccac6c709e61072fcfad968f4bb8016bc272f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFRS4AB62AACDBK7QXXPWZZPTU/bundle.json","state_url":"https://pith.science/pith/BFRS4AB62AACDBK7QXXPWZZPTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFRS4AB62AACDBK7QXXPWZZPTU/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":"2026-08-22T19:33:20Z","links":{"resolver":"https://pith.science/pith/BFRS4AB62AACDBK7QXXPWZZPTU","bundle":"https://pith.science/pith/BFRS4AB62AACDBK7QXXPWZZPTU/bundle.json","state":"https://pith.science/pith/BFRS4AB62AACDBK7QXXPWZZPTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFRS4AB62AACDBK7QXXPWZZPTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BFRS4AB62AACDBK7QXXPWZZPTU","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":"ae5550531657839f9c742415fc77d7d1b6c49734694f23d98499773fbcd56d84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T08:25:26Z","title_canon_sha256":"d2d063a2b1034aeb5cc961231b71ef9202b4d187bfd325557ce5eef29c091d62"},"schema_version":"1.0","source":{"id":"2408.01708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01708","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01708v1","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01708","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"BFRS4AB62AAC","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"BFRS4AB62AACDBK7","created_at":"2026-07-05T08:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"BFRS4AB6","created_at":"2026-07-05T08:52:01Z"}],"graph_snapshots":[{"event_id":"sha256:28ba87ee012f3b4e2edd8f08dccccac6c709e61072fcfad968f4bb8016bc272f","target":"graph","created_at":"2026-07-05T08:52:01Z","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/2408.01708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the network, we identify two key obstacles in AVS models: 1) attention dissipation, corresponding to the over-concentrated attention weights by Softmax within restricted frames, and 2) inefficient, burdensome transformer decoder, caused by narrow focus patterns in early stages. In this paper, we introduce AVESFormer, the first real-time Audio-Visual Efficient S","authors_text":"Fei Li, Jiazhong Yu, Linsu Shi, Qinghua Liang, Qi Yang, Shiming Xiang, Zili Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T08:25:26Z","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01708","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":"sha256:6de54f1be024292954b6cc254898660633b06b56ca15b7ca01a731c55052d82a","target":"record","created_at":"2026-07-05T08:52:01Z","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":"ae5550531657839f9c742415fc77d7d1b6c49734694f23d98499773fbcd56d84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T08:25:26Z","title_canon_sha256":"d2d063a2b1034aeb5cc961231b71ef9202b4d187bfd325557ce5eef29c091d62"},"schema_version":"1.0","source":{"id":"2408.01708","kind":"arxiv","version":1}},"canonical_sha256":"09632e003ed00021855f85eefb672f9d1b12de3a0875e3f25e712d1a72bc71e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09632e003ed00021855f85eefb672f9d1b12de3a0875e3f25e712d1a72bc71e7","first_computed_at":"2026-07-05T08:52:01.646646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:01.646646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ut5BTl0fuvBrXixkRmCnG/cwHBlueeLJRJbCoK4MoJrAx9qaBjSYGF0+RD82UwDEm8e/uX4Mhw7AR3upqh+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:01.647046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6de54f1be024292954b6cc254898660633b06b56ca15b7ca01a731c55052d82a","sha256:28ba87ee012f3b4e2edd8f08dccccac6c709e61072fcfad968f4bb8016bc272f"],"state_sha256":"9196263ed27861a66e60d0d9cd0fee3c5f9ef99ea02cc362ba8d6bac13495624"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U90PBRzACwoCJj2YrR8gKcsO3box6X7jprXywAT1P43T+H9NxnciafCepHYqnRNdmxhDPHwQToY7ZvWOJiBBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T19:33:20.040419Z","bundle_sha256":"9c34c2d1c098b207c269fd884bccc3f5dc7197baea5b77d99f5df399f1bd436e"}}