{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EM3432IZJ3HB4V2FXMRRU3SFMC","short_pith_number":"pith:EM3432IZ","canonical_record":{"source":{"id":"2309.07929","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:43:35Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"d49ce3c69f9896e7a1ba8f798ca887b1e9b72cfcd50d95fc66a59b53f82ca0cb","abstract_canon_sha256":"6bcd2edc86f13361c6504fd7e32fa68d58ea708aebce9abbc75bfd58f0c5024b"},"schema_version":"1.0"},"canonical_sha256":"2337cde9194ece1e5745bb231a6e45609240544059a2f41d115c60d2417cfc1c","source":{"kind":"arxiv","id":"2309.07929","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07929","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07929v3","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07929","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"EM3432IZJ3HB","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"EM3432IZJ3HB4V2F","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"EM3432IZ","created_at":"2026-07-05T07:40:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EM3432IZJ3HB4V2FXMRRU3SFMC","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07929","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:43:35Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"d49ce3c69f9896e7a1ba8f798ca887b1e9b72cfcd50d95fc66a59b53f82ca0cb","abstract_canon_sha256":"6bcd2edc86f13361c6504fd7e32fa68d58ea708aebce9abbc75bfd58f0c5024b"},"schema_version":"1.0"},"canonical_sha256":"2337cde9194ece1e5745bb231a6e45609240544059a2f41d115c60d2417cfc1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:23.085140Z","signature_b64":"6672GyWDbmJWRrO4fAo3rrlihskl7gKyja8gE0ca4QGSrF7114N+PqsNI+TF9NDbb8O1zSLEAVigdM5quBg8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2337cde9194ece1e5745bb231a6e45609240544059a2f41d115c60d2417cfc1c","last_reissued_at":"2026-07-05T07:40:23.084660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:23.084660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07929","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NKu3Rs3kdKYYzo0O98Xn/okwy+kurXtRVm8amnqJOjz6bItYvPBqkyR1j8+2fVWXs70hBPTzLVFOSp7hpb/BDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:53:15.690467Z"},"content_sha256":"50fd348761bfda992f8b24e8155e6ee31a3f37ceda92d077d5585815f621efe2","schema_version":"1.0","event_id":"sha256:50fd348761bfda992f8b24e8155e6ee31a3f37ceda92d077d5585815f621efe2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EM3432IZJ3HB4V2FXMRRU3SFMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","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":"Di Hu, Guangyao Li, Jian Ding, Weisong Liu, Xi Li, Yaoting Wang","submitted_at":"2023-09-13T05:43:35Z","abstract_excerpt":"Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07929","kind":"arxiv","version":3},"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/2309.07929/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":"2026-07-05T07:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0HSmGawiXAYSubkhHj3PaXbyLt42jj6PuSWRkxlByR0tWE8Muu1jMC2l+C3NnOJ0r0FAVU4hGAV4/beLQTdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:53:15.690986Z"},"content_sha256":"71e4b1ce212f7f3f3d56522b3cc8105c978b7d015df5c216f2fa5aaa18bfd556","schema_version":"1.0","event_id":"sha256:71e4b1ce212f7f3f3d56522b3cc8105c978b7d015df5c216f2fa5aaa18bfd556"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/bundle.json","state_url":"https://pith.science/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/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":"2026-08-07T19:53:15Z","links":{"resolver":"https://pith.science/pith/EM3432IZJ3HB4V2FXMRRU3SFMC","bundle":"https://pith.science/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/bundle.json","state":"https://pith.science/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EM3432IZJ3HB4V2FXMRRU3SFMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EM3432IZJ3HB4V2FXMRRU3SFMC","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":"6bcd2edc86f13361c6504fd7e32fa68d58ea708aebce9abbc75bfd58f0c5024b","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":"2023-09-13T05:43:35Z","title_canon_sha256":"d49ce3c69f9896e7a1ba8f798ca887b1e9b72cfcd50d95fc66a59b53f82ca0cb"},"schema_version":"1.0","source":{"id":"2309.07929","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07929","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07929v3","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07929","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"EM3432IZJ3HB","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"EM3432IZJ3HB4V2F","created_at":"2026-07-05T07:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"EM3432IZ","created_at":"2026-07-05T07:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:71e4b1ce212f7f3f3d56522b3cc8105c978b7d015df5c216f2fa5aaa18bfd556","target":"graph","created_at":"2026-07-05T07:40:23Z","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/2309.07929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas","authors_text":"Di Hu, Guangyao Li, Jian Ding, Weisong Liu, Xi Li, Yaoting Wang","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":"2023-09-13T05:43:35Z","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07929","kind":"arxiv","version":3},"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":"sha256:50fd348761bfda992f8b24e8155e6ee31a3f37ceda92d077d5585815f621efe2","target":"record","created_at":"2026-07-05T07:40:23Z","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":"6bcd2edc86f13361c6504fd7e32fa68d58ea708aebce9abbc75bfd58f0c5024b","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":"2023-09-13T05:43:35Z","title_canon_sha256":"d49ce3c69f9896e7a1ba8f798ca887b1e9b72cfcd50d95fc66a59b53f82ca0cb"},"schema_version":"1.0","source":{"id":"2309.07929","kind":"arxiv","version":3}},"canonical_sha256":"2337cde9194ece1e5745bb231a6e45609240544059a2f41d115c60d2417cfc1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2337cde9194ece1e5745bb231a6e45609240544059a2f41d115c60d2417cfc1c","first_computed_at":"2026-07-05T07:40:23.084660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:23.084660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6672GyWDbmJWRrO4fAo3rrlihskl7gKyja8gE0ca4QGSrF7114N+PqsNI+TF9NDbb8O1zSLEAVigdM5quBg8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:23.085140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07929","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50fd348761bfda992f8b24e8155e6ee31a3f37ceda92d077d5585815f621efe2","sha256:71e4b1ce212f7f3f3d56522b3cc8105c978b7d015df5c216f2fa5aaa18bfd556"],"state_sha256":"7d746ec3c9992c3287191fc1b45f2f0265112fd83d82aff0229423a53fdcab91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNg9Pb2xfl2X6b1kLXcmTJHYUbKyINhUkOmNQx8yrx+FsFj2Bi/DrLRo+HWvpKt5VeouMAq2FiMRy8pMGvc0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:53:15.697231Z","bundle_sha256":"b764fd6edea5447ecbc294e3215998ee761b1449461d7fe961e494c72c34df3a"}}