{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FPVYWRYTRAWCYJL7K5SBE2PH7B","short_pith_number":"pith:FPVYWRYT","schema_version":"1.0","canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","source":{"kind":"arxiv","id":"2607.24786","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Spatial Grounding in Large Audio-Visual Retrieval models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Ga\\\"el Richard, Hugo Malard, Michel Olvera, Sanjeel Parekh, Slim Essid, St\\'ephane Lathuili\\`ere","submitted_at":"2026-06-22T11:13:25Z","abstract_excerpt":"Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The task, however, remains challenging, as models must locate sound sources from temporally aligned audio-visual data without pixel-level supervision. Recent large-scale audio-visual retrieval models, trained at unprecedented scale, encode rich multimodal structure. We show their latent representations, though optimized for global alignment, can nonetheless enable fine-grained spatial grounding. While spatial detail is progressively lost in the upper l"},"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":"2607.24786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T11:13:25Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"b26a6032bcdbc41a4c6301051cd53f60019ba9df47f7dca93a8e9cc6c65c6d70","abstract_canon_sha256":"3870e96d8dae28c266ecf3004d7d49f3f4dcf9b402f9b08552bb6343f22c1f99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:44.016576Z","signature_b64":"WHj8np6gygG3m9AKlDKAdvXCi4iekUbA9E/tVdWOXkoN54AS5kOqgupNV6YKvUz1y8gz9hduxcDEic8zE1MxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","last_reissued_at":"2026-07-29T00:24:44.015745Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:44.015745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Spatial Grounding in Large Audio-Visual Retrieval models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Ga\\\"el Richard, Hugo Malard, Michel Olvera, Sanjeel Parekh, Slim Essid, St\\'ephane Lathuili\\`ere","submitted_at":"2026-06-22T11:13:25Z","abstract_excerpt":"Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The task, however, remains challenging, as models must locate sound sources from temporally aligned audio-visual data without pixel-level supervision. Recent large-scale audio-visual retrieval models, trained at unprecedented scale, encode rich multimodal structure. We show their latent representations, though optimized for global alignment, can nonetheless enable fine-grained spatial grounding. While spatial detail is progressively lost in the upper l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24786","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/2607.24786/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24786","created_at":"2026-07-29T00:24:44.016171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24786v1","created_at":"2026-07-29T00:24:44.016171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24786","created_at":"2026-07-29T00:24:44.016171+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPVYWRYTRAWC","created_at":"2026-07-29T00:24:44.016171+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPVYWRYTRAWCYJL7","created_at":"2026-07-29T00:24:44.016171+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPVYWRYT","created_at":"2026-07-29T00:24:44.016171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B","json":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B.json","graph_json":"https://pith.science/api/pith-number/FPVYWRYTRAWCYJL7K5SBE2PH7B/graph.json","events_json":"https://pith.science/api/pith-number/FPVYWRYTRAWCYJL7K5SBE2PH7B/events.json","paper":"https://pith.science/paper/FPVYWRYT"},"agent_actions":{"view_html":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B","download_json":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B.json","view_paper":"https://pith.science/paper/FPVYWRYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24786&json=true","fetch_graph":"https://pith.science/api/pith-number/FPVYWRYTRAWCYJL7K5SBE2PH7B/graph.json","fetch_events":"https://pith.science/api/pith-number/FPVYWRYTRAWCYJL7K5SBE2PH7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/action/storage_attestation","attest_author":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/action/author_attestation","sign_citation":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/action/citation_signature","submit_replication":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/action/replication_record"}},"created_at":"2026-07-29T00:24:44.016171+00:00","updated_at":"2026-07-29T00:24:44.016171+00:00"}