{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:64H5YCYK3QNARIFUUSLDE7NQEO","short_pith_number":"pith:64H5YCYK","canonical_record":{"source":{"id":"2508.03724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"ed8ac4d3ef56156c3c3fccd34498e724ef7c40e2e7e5929b8abe83d14afb1af9","abstract_canon_sha256":"8441bd9e937df4736bd749b2ce3a332cdd64cdd4c720b0008919016a29293ccd"},"schema_version":"1.0"},"canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","source":{"kind":"arxiv","id":"2508.03724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03724","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03724v1","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03724","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"64H5YCYK3QNA","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"64H5YCYK3QNARIFU","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"64H5YCYK","created_at":"2026-07-05T11:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:64H5YCYK3QNARIFUUSLDE7NQEO","target":"record","payload":{"canonical_record":{"source":{"id":"2508.03724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"ed8ac4d3ef56156c3c3fccd34498e724ef7c40e2e7e5929b8abe83d14afb1af9","abstract_canon_sha256":"8441bd9e937df4736bd749b2ce3a332cdd64cdd4c720b0008919016a29293ccd"},"schema_version":"1.0"},"canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:13.673445Z","signature_b64":"UfCdlB2D/t2P2eVKwa1+z9pTNzXwHaGwI8M+ejCOr2rmf+dY25T/OvhDXV7YavXkoI54WHYzZ27LM7WAgp4ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","last_reissued_at":"2026-07-05T11:49:13.672888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:13.672888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.03724","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":"2026-07-05T11:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruTaK3mrvzPmpgkOqMPPt7ouA6zvp/o00uGQl65G4kyswEOa/H1fFk6FKK2EYKlkpGLppH29uox99f3CRNtsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:07.899914Z"},"content_sha256":"fda7d4fc0b276e486b710fb09bae2721b6b13b14101da2f45ba641bc1d5bae95","schema_version":"1.0","event_id":"sha256:fda7d4fc0b276e486b710fb09bae2721b6b13b14101da2f45ba641bc1d5bae95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:64H5YCYK3QNARIFUUSLDE7NQEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Li, Yapeng Tian","submitted_at":"2025-07-29T22:20:51Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained object-level understanding. In this survey, we present a comprehensive overview of the AVS field, covering its problem formulation, benchmark datasets, evaluation metrics, and the progression of methodologies. We analyze a wide range of approaches, including architectures for unimodal and multimodal encoding, key strategies for audio-visual fusion, and various "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03724","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/2508.03724/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":"2026-07-05T11:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uovS8OEShQXJr6dPTwMj8Uy7EHR/KElfJrXObEjNsXRzosXsIDs86BlCi0vWm3Kaze0nB7aCE2xJte0jI5CmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:07.900461Z"},"content_sha256":"7afc446036e1ad21e6f1324361ab6f17e0fe0ee3158f9a82cb67f0f3658b6ac6","schema_version":"1.0","event_id":"sha256:7afc446036e1ad21e6f1324361ab6f17e0fe0ee3158f9a82cb67f0f3658b6ac6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/bundle.json","state_url":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64H5YCYK3QNARIFUUSLDE7NQEO/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":"2026-08-04T22:38:07Z","links":{"resolver":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO","bundle":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/bundle.json","state":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64H5YCYK3QNARIFUUSLDE7NQEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:64H5YCYK3QNARIFUUSLDE7NQEO","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":"8441bd9e937df4736bd749b2ce3a332cdd64cdd4c720b0008919016a29293ccd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","title_canon_sha256":"ed8ac4d3ef56156c3c3fccd34498e724ef7c40e2e7e5929b8abe83d14afb1af9"},"schema_version":"1.0","source":{"id":"2508.03724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03724","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03724v1","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03724","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"64H5YCYK3QNA","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"64H5YCYK3QNARIFU","created_at":"2026-07-05T11:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"64H5YCYK","created_at":"2026-07-05T11:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:7afc446036e1ad21e6f1324361ab6f17e0fe0ee3158f9a82cb67f0f3658b6ac6","target":"graph","created_at":"2026-07-05T11:49:13Z","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/2508.03724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained object-level understanding. In this survey, we present a comprehensive overview of the AVS field, covering its problem formulation, benchmark datasets, evaluation metrics, and the progression of methodologies. We analyze a wide range of approaches, including architectures for unimodal and multimodal encoding, key strategies for audio-visual fusion, and various ","authors_text":"Jia Li, Yapeng Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03724","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:fda7d4fc0b276e486b710fb09bae2721b6b13b14101da2f45ba641bc1d5bae95","target":"record","created_at":"2026-07-05T11:49:13Z","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":"8441bd9e937df4736bd749b2ce3a332cdd64cdd4c720b0008919016a29293ccd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","title_canon_sha256":"ed8ac4d3ef56156c3c3fccd34498e724ef7c40e2e7e5929b8abe83d14afb1af9"},"schema_version":"1.0","source":{"id":"2508.03724","kind":"arxiv","version":1}},"canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","first_computed_at":"2026-07-05T11:49:13.672888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:13.672888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UfCdlB2D/t2P2eVKwa1+z9pTNzXwHaGwI8M+ejCOr2rmf+dY25T/OvhDXV7YavXkoI54WHYzZ27LM7WAgp4ADA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:13.673445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fda7d4fc0b276e486b710fb09bae2721b6b13b14101da2f45ba641bc1d5bae95","sha256:7afc446036e1ad21e6f1324361ab6f17e0fe0ee3158f9a82cb67f0f3658b6ac6"],"state_sha256":"3c6fb53b635e8ffbcefd9673fc0bf131306305b5825653b0fc4906dcff1b3bbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScfclJjJeOelv6ZZzIOTVh8S3ri3WER8n9x0Wpp81ZXVC2DTinLlkg0ribiZsAuq+9FlejKlX8D8VnZ7C4frBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:38:07.905696Z","bundle_sha256":"23311d62af22feea5b000ea586f62d8f5af818cd7235e920f521009a2c546bb4"}}