{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJEFPVP22W6ILWI5QTLY6NJYSW","short_pith_number":"pith:DJEFPVP2","schema_version":"1.0","canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","source":{"kind":"arxiv","id":"2506.01015","version":2},"attestation_state":"computed","paper":{"title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Peng, Chong Wang, Gustavo Carneiro, Jingkun Chen, Junde Wu, Junlin Han, Yuanhong Chen, Yu Tian, Yuyuan Liu","submitted_at":"2025-06-01T13:57:42Z","abstract_excerpt":"Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it prop"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.01015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","cross_cats_sorted":[],"title_canon_sha256":"3151298b311700ac8a429be5122fe5a4265c4574348f4e621972a21af027ec20","abstract_canon_sha256":"12a42ed259c8931623181647fe1c20491ffa8ed45985b3861d794e5d7d04c5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:01.304735Z","signature_b64":"+W578p+eIi9Giinw7igsyOuSAAHmOd+2WXlkuyraSclTJ71pG2tEEtHW/wnUkAYugjOVHrN28SXnIf8ejf9EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","last_reissued_at":"2026-05-17T23:39:01.304097Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:01.304097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Peng, Chong Wang, Gustavo Carneiro, Jingkun Chen, Junde Wu, Junlin Han, Yuanhong Chen, Yu Tian, Yuyuan Liu","submitted_at":"2025-06-01T13:57:42Z","abstract_excerpt":"Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01015","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.01015","created_at":"2026-05-17T23:39:01.304211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01015v2","created_at":"2026-05-17T23:39:01.304211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01015","created_at":"2026-05-17T23:39:01.304211+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJEFPVP22W6I","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJEFPVP22W6ILWI5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJEFPVP2","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW","json":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW.json","graph_json":"https://pith.science/api/pith-number/DJEFPVP22W6ILWI5QTLY6NJYSW/graph.json","events_json":"https://pith.science/api/pith-number/DJEFPVP22W6ILWI5QTLY6NJYSW/events.json","paper":"https://pith.science/paper/DJEFPVP2"},"agent_actions":{"view_html":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW","download_json":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW.json","view_paper":"https://pith.science/paper/DJEFPVP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01015&json=true","fetch_graph":"https://pith.science/api/pith-number/DJEFPVP22W6ILWI5QTLY6NJYSW/graph.json","fetch_events":"https://pith.science/api/pith-number/DJEFPVP22W6ILWI5QTLY6NJYSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/action/storage_attestation","attest_author":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/action/author_attestation","sign_citation":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/action/citation_signature","submit_replication":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/action/replication_record"}},"created_at":"2026-05-17T23:39:01.304211+00:00","updated_at":"2026-05-17T23:39:01.304211+00:00"}