{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YNKD7XE5A5UB5JQXGTPHXYC7AK","short_pith_number":"pith:YNKD7XE5","canonical_record":{"source":{"id":"2305.01836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T00:33:52Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"b1d2781013be47241e2ff1ccd55cbc4a9aabf39fbdb2c1a9f24efb321b3d474e","abstract_canon_sha256":"b5c5c6978f48b498796eb9644e5a4e51418ae6622e779b3f3c9d39e730fa2e06"},"schema_version":"1.0"},"canonical_sha256":"c3543fdc9d07681ea61734de7be05f02a20ddd7b1148c7508cfb83102502420b","source":{"kind":"arxiv","id":"2305.01836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01836","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01836v1","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01836","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"YNKD7XE5A5UB","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"YNKD7XE5A5UB5JQX","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"YNKD7XE5","created_at":"2026-07-05T06:06:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YNKD7XE5A5UB5JQXGTPHXYC7AK","target":"record","payload":{"canonical_record":{"source":{"id":"2305.01836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T00:33:52Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"b1d2781013be47241e2ff1ccd55cbc4a9aabf39fbdb2c1a9f24efb321b3d474e","abstract_canon_sha256":"b5c5c6978f48b498796eb9644e5a4e51418ae6622e779b3f3c9d39e730fa2e06"},"schema_version":"1.0"},"canonical_sha256":"c3543fdc9d07681ea61734de7be05f02a20ddd7b1148c7508cfb83102502420b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:32.960292Z","signature_b64":"Kv9LZRn54agtZgUGej/wwj1SairEAHzVLkCqKov2L12UrJ650UsFZoCDgb4HAiv4DIg/0E1gR/FLdl6hIAudDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3543fdc9d07681ea61734de7be05f02a20ddd7b1148c7508cfb83102502420b","last_reissued_at":"2026-07-05T06:06:32.959882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:32.959882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.01836","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":"2026-07-05T06:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+l2BHcYRVB7f7tAZmGWr6Ry/AMTCisCGQ6SC7A1/8L605aqurFKE5PBjj7Q0GXQGYp1IlJCsHVEl36mEvWuSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:20:24.161958Z"},"content_sha256":"e19a53921b5c878d45b2c1fa179abc92fab791056dc8410899efbc526e0ded7a","schema_version":"1.0","event_id":"sha256:e19a53921b5c878d45b2c1fa179abc92fab791056dc8410899efbc526e0ded7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YNKD7XE5A5UB5JQXGTPHXYC7AK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Shentong Mo, Yapeng Tian","submitted_at":"2023-05-03T00:33:52Z","abstract_excerpt":"Segment Anything Model (SAM) has recently shown its powerful effectiveness in visual segmentation tasks. However, there is less exploration concerning how SAM works on audio-visual tasks, such as visual sound localization and segmentation. In this work, we propose a simple yet effective audio-visual localization and segmentation framework based on the Segment Anything Model, namely AV-SAM, that can generate sounding object masks corresponding to the audio. Specifically, our AV-SAM simply leverages pixel-wise audio-visual fusion across audio features and visual features from the pre-trained ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01836","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/2305.01836/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":"2026-07-05T06:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aj58jKgMC2kUJ+8QDM+KzF7Csk/p1lkNHcuO8+IobqEbbpMG+6WRQYQFjYb25VHalGHToUWIfuhFQYinjZxTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:20:24.162475Z"},"content_sha256":"8e6fe4d2566731a6d7af5b9a04c4ae0706c56a2f22d0b2180e76103a018871d6","schema_version":"1.0","event_id":"sha256:8e6fe4d2566731a6d7af5b9a04c4ae0706c56a2f22d0b2180e76103a018871d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/bundle.json","state_url":"https://pith.science/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/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":"2026-08-09T00:20:24Z","links":{"resolver":"https://pith.science/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK","bundle":"https://pith.science/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/bundle.json","state":"https://pith.science/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNKD7XE5A5UB5JQXGTPHXYC7AK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YNKD7XE5A5UB5JQXGTPHXYC7AK","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":"b5c5c6978f48b498796eb9644e5a4e51418ae6622e779b3f3c9d39e730fa2e06","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T00:33:52Z","title_canon_sha256":"b1d2781013be47241e2ff1ccd55cbc4a9aabf39fbdb2c1a9f24efb321b3d474e"},"schema_version":"1.0","source":{"id":"2305.01836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01836","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01836v1","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01836","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"YNKD7XE5A5UB","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"YNKD7XE5A5UB5JQX","created_at":"2026-07-05T06:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"YNKD7XE5","created_at":"2026-07-05T06:06:32Z"}],"graph_snapshots":[{"event_id":"sha256:8e6fe4d2566731a6d7af5b9a04c4ae0706c56a2f22d0b2180e76103a018871d6","target":"graph","created_at":"2026-07-05T06:06:32Z","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/2305.01836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segment Anything Model (SAM) has recently shown its powerful effectiveness in visual segmentation tasks. However, there is less exploration concerning how SAM works on audio-visual tasks, such as visual sound localization and segmentation. In this work, we propose a simple yet effective audio-visual localization and segmentation framework based on the Segment Anything Model, namely AV-SAM, that can generate sounding object masks corresponding to the audio. Specifically, our AV-SAM simply leverages pixel-wise audio-visual fusion across audio features and visual features from the pre-trained ima","authors_text":"Shentong Mo, Yapeng Tian","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T00:33:52Z","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01836","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:e19a53921b5c878d45b2c1fa179abc92fab791056dc8410899efbc526e0ded7a","target":"record","created_at":"2026-07-05T06:06:32Z","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":"b5c5c6978f48b498796eb9644e5a4e51418ae6622e779b3f3c9d39e730fa2e06","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T00:33:52Z","title_canon_sha256":"b1d2781013be47241e2ff1ccd55cbc4a9aabf39fbdb2c1a9f24efb321b3d474e"},"schema_version":"1.0","source":{"id":"2305.01836","kind":"arxiv","version":1}},"canonical_sha256":"c3543fdc9d07681ea61734de7be05f02a20ddd7b1148c7508cfb83102502420b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3543fdc9d07681ea61734de7be05f02a20ddd7b1148c7508cfb83102502420b","first_computed_at":"2026-07-05T06:06:32.959882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:06:32.959882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kv9LZRn54agtZgUGej/wwj1SairEAHzVLkCqKov2L12UrJ650UsFZoCDgb4HAiv4DIg/0E1gR/FLdl6hIAudDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:06:32.960292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e19a53921b5c878d45b2c1fa179abc92fab791056dc8410899efbc526e0ded7a","sha256:8e6fe4d2566731a6d7af5b9a04c4ae0706c56a2f22d0b2180e76103a018871d6"],"state_sha256":"4eec2c37dba1cc2b82c697f5135709bce88414e61ea0491772f8435e49e822b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jq8VqdP/jUxQuq16ECk35T4gWk2oO3/Op5ATqmJdn67aA2/VxbnzZd92eAabh+SLrR6+JrjDff2xSzMMgm6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:20:24.167370Z","bundle_sha256":"c5224813bb8ece03a24c4dd3eef6268bd47556c54386e9ab6e3736ba2b9c02e0"}}