{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P7STANBJKRNEGFBTJWCVWGVHAU","short_pith_number":"pith:P7STANBJ","canonical_record":{"source":{"id":"2406.09167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T14:28:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6ea4636d4a3634823149fb4e71b356bde77648ebc0ede600f354bc697ebfd075","abstract_canon_sha256":"8df6ced4523b04e4bc1ef8e3000c43802b11bb203637c40379084caf3e037e38"},"schema_version":"1.0"},"canonical_sha256":"7fe5303429545a4314334d855b1aa7052543f46a5205b9700ead83b91aae7e99","source":{"kind":"arxiv","id":"2406.09167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09167","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09167v1","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09167","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"P7STANBJKRNE","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"P7STANBJKRNEGFBT","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"P7STANBJ","created_at":"2026-07-05T08:31:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P7STANBJKRNEGFBTJWCVWGVHAU","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T14:28:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6ea4636d4a3634823149fb4e71b356bde77648ebc0ede600f354bc697ebfd075","abstract_canon_sha256":"8df6ced4523b04e4bc1ef8e3000c43802b11bb203637c40379084caf3e037e38"},"schema_version":"1.0"},"canonical_sha256":"7fe5303429545a4314334d855b1aa7052543f46a5205b9700ead83b91aae7e99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:29.425162Z","signature_b64":"zniMDykpipLv96N8tNc3/iyQs/UaGnZUSZoNZ16GqOEdriwuwXynxITCuOLq2XSH/eEorrge2E/fU5cNaVY+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe5303429545a4314334d855b1aa7052543f46a5205b9700ead83b91aae7e99","last_reissued_at":"2026-07-05T08:31:29.424656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:29.424656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09167","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":"2026-07-05T08:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6DHmj18ozYaxaLiCo0RWzi9Zp0KSorNCy3ACAt1nSNH7Dlo7Htqb1ZVBnO2bf2SOu3KhTtKk+pYiW5i2mxPuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:40:53.105732Z"},"content_sha256":"f08607fa9f456508fe4e2229a882093866bb7bd24d71f0db37bb6c9bb8973d0e","schema_version":"1.0","event_id":"sha256:f08607fa9f456508fe4e2229a882093866bb7bd24d71f0db37bb6c9bb8973d0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P7STANBJKRNEGFBTJWCVWGVHAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision Transformer Segmentation for Visual Bird Sound Denoising","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jialu Li, Sahil Kumar, Youshan Zhang","submitted_at":"2024-06-13T14:28:37Z","abstract_excerpt":"Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose ViTVS, a novel approach that leverages the power of the vision transformer (ViT) architecture. ViTVS adeptly combines segmentation techniques to disentangle clean audio from complex signal mixtures. Our key contributions encompass the development of ViTVS, introducing comprehensive, long-range, and multi-scale representations. These contributions directly tack"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09167","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/2406.09167/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":"2026-07-05T08:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEKDR15K2/wNAhcIKoZ1WzR/JNcS9eqSC8HYkV+AgSGV6ee4PXgk2p38rKDwgAw1R2HOfmaioxlP0iqFK+8LBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:40:53.106279Z"},"content_sha256":"da16d0755c9c2c16c68f68026afeb28f1b2cd45c054d955238e4d3f14f13379a","schema_version":"1.0","event_id":"sha256:da16d0755c9c2c16c68f68026afeb28f1b2cd45c054d955238e4d3f14f13379a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7STANBJKRNEGFBTJWCVWGVHAU/bundle.json","state_url":"https://pith.science/pith/P7STANBJKRNEGFBTJWCVWGVHAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7STANBJKRNEGFBTJWCVWGVHAU/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":"2026-08-09T00:40:53Z","links":{"resolver":"https://pith.science/pith/P7STANBJKRNEGFBTJWCVWGVHAU","bundle":"https://pith.science/pith/P7STANBJKRNEGFBTJWCVWGVHAU/bundle.json","state":"https://pith.science/pith/P7STANBJKRNEGFBTJWCVWGVHAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7STANBJKRNEGFBTJWCVWGVHAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P7STANBJKRNEGFBTJWCVWGVHAU","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":"8df6ced4523b04e4bc1ef8e3000c43802b11bb203637c40379084caf3e037e38","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T14:28:37Z","title_canon_sha256":"6ea4636d4a3634823149fb4e71b356bde77648ebc0ede600f354bc697ebfd075"},"schema_version":"1.0","source":{"id":"2406.09167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09167","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09167v1","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09167","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"P7STANBJKRNE","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"P7STANBJKRNEGFBT","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"P7STANBJ","created_at":"2026-07-05T08:31:29Z"}],"graph_snapshots":[{"event_id":"sha256:da16d0755c9c2c16c68f68026afeb28f1b2cd45c054d955238e4d3f14f13379a","target":"graph","created_at":"2026-07-05T08:31:29Z","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/2406.09167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose ViTVS, a novel approach that leverages the power of the vision transformer (ViT) architecture. ViTVS adeptly combines segmentation techniques to disentangle clean audio from complex signal mixtures. Our key contributions encompass the development of ViTVS, introducing comprehensive, long-range, and multi-scale representations. These contributions directly tack","authors_text":"Jialu Li, Sahil Kumar, Youshan Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T14:28:37Z","title":"Vision Transformer Segmentation for Visual Bird Sound Denoising"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09167","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:f08607fa9f456508fe4e2229a882093866bb7bd24d71f0db37bb6c9bb8973d0e","target":"record","created_at":"2026-07-05T08:31:29Z","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":"8df6ced4523b04e4bc1ef8e3000c43802b11bb203637c40379084caf3e037e38","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T14:28:37Z","title_canon_sha256":"6ea4636d4a3634823149fb4e71b356bde77648ebc0ede600f354bc697ebfd075"},"schema_version":"1.0","source":{"id":"2406.09167","kind":"arxiv","version":1}},"canonical_sha256":"7fe5303429545a4314334d855b1aa7052543f46a5205b9700ead83b91aae7e99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fe5303429545a4314334d855b1aa7052543f46a5205b9700ead83b91aae7e99","first_computed_at":"2026-07-05T08:31:29.424656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:29.424656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zniMDykpipLv96N8tNc3/iyQs/UaGnZUSZoNZ16GqOEdriwuwXynxITCuOLq2XSH/eEorrge2E/fU5cNaVY+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:29.425162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f08607fa9f456508fe4e2229a882093866bb7bd24d71f0db37bb6c9bb8973d0e","sha256:da16d0755c9c2c16c68f68026afeb28f1b2cd45c054d955238e4d3f14f13379a"],"state_sha256":"f338a12632b85221dacf304cf4bfbb287d711d0b50cc0e6ae3458ba0f0296707"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlm5fL8c1Lx3UIGC6afNif1wHxhM5vWMRr661lQN1X/Pm6ENnl+rdYfu4S4o+YMM6YUGI2CJFvCgu4XTkHuJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:40:53.110705Z","bundle_sha256":"65522b7a59bdade38c88b73821dc41db30902f1620f1ab4933c0fb195393165a"}}