{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FPVYWRYTRAWCYJL7K5SBE2PH7B","short_pith_number":"pith:FPVYWRYT","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"},"canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","source":{"kind":"arxiv","id":"2607.24786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24786","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24786v1","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24786","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"FPVYWRYTRAWC","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"FPVYWRYTRAWCYJL7","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"FPVYWRYT","created_at":"2026-07-29T00:24:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FPVYWRYTRAWCYJL7K5SBE2PH7B","target":"record","payload":{"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"},"canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","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"},"source_kind":"arxiv","source_id":"2607.24786","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":"2026-07-29T00:24:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gHYvIPils6yHooT2HG7WYpsviU78xhJRe4NXTm/wdCjui9vfMpsn3BEAFv0u4AYiKPpGmKrzFBYx2JJzYTmxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:40:09.823205Z"},"content_sha256":"b4c2aac9bdd87a1b9c460b5566725c0e1ac2705c2d48168c48b08185b9adb295","schema_version":"1.0","event_id":"sha256:b4c2aac9bdd87a1b9c460b5566725c0e1ac2705c2d48168c48b08185b9adb295"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FPVYWRYTRAWCYJL7K5SBE2PH7B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:24:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+HHzMupuD5GRUJj8CiCgoHTB9v1p3Jofqw2Q7Oz9U4bsqR3HFO0vB35ff64XmenR7PfpgH/zILB6gcGki3m5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:40:09.823724Z"},"content_sha256":"0aa25c9b7e315a8d3b84efbaefa2c986d5c5ba57726e0c437d08b12e568a2998","schema_version":"1.0","event_id":"sha256:0aa25c9b7e315a8d3b84efbaefa2c986d5c5ba57726e0c437d08b12e568a2998"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/bundle.json","state_url":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/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":"2026-08-08T09:40:09Z","links":{"resolver":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B","bundle":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/bundle.json","state":"https://pith.science/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPVYWRYTRAWCYJL7K5SBE2PH7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FPVYWRYTRAWCYJL7K5SBE2PH7B","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":"3870e96d8dae28c266ecf3004d7d49f3f4dcf9b402f9b08552bb6343f22c1f99","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T11:13:25Z","title_canon_sha256":"b26a6032bcdbc41a4c6301051cd53f60019ba9df47f7dca93a8e9cc6c65c6d70"},"schema_version":"1.0","source":{"id":"2607.24786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24786","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24786v1","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24786","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"FPVYWRYTRAWC","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"FPVYWRYTRAWCYJL7","created_at":"2026-07-29T00:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"FPVYWRYT","created_at":"2026-07-29T00:24:44Z"}],"graph_snapshots":[{"event_id":"sha256:0aa25c9b7e315a8d3b84efbaefa2c986d5c5ba57726e0c437d08b12e568a2998","target":"graph","created_at":"2026-07-29T00:24:44Z","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/2607.24786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ga\\\"el Richard, Hugo Malard, Michel Olvera, Sanjeel Parekh, Slim Essid, St\\'ephane Lathuili\\`ere","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T11:13:25Z","title":"Unlocking Spatial Grounding in Large Audio-Visual Retrieval models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24786","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:b4c2aac9bdd87a1b9c460b5566725c0e1ac2705c2d48168c48b08185b9adb295","target":"record","created_at":"2026-07-29T00:24:44Z","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":"3870e96d8dae28c266ecf3004d7d49f3f4dcf9b402f9b08552bb6343f22c1f99","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T11:13:25Z","title_canon_sha256":"b26a6032bcdbc41a4c6301051cd53f60019ba9df47f7dca93a8e9cc6c65c6d70"},"schema_version":"1.0","source":{"id":"2607.24786","kind":"arxiv","version":1}},"canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2beb8b4713882c2c257f57641269e7f85998d6cbeb7f74a21d2fc37aecebdeee","first_computed_at":"2026-07-29T00:24:44.015745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:44.015745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WHj8np6gygG3m9AKlDKAdvXCi4iekUbA9E/tVdWOXkoN54AS5kOqgupNV6YKvUz1y8gz9hduxcDEic8zE1MxAA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:44.016576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4c2aac9bdd87a1b9c460b5566725c0e1ac2705c2d48168c48b08185b9adb295","sha256:0aa25c9b7e315a8d3b84efbaefa2c986d5c5ba57726e0c437d08b12e568a2998"],"state_sha256":"aa640510b0dc9e13e97c56b8343240d41470f59d04f80e0f4c86654fd58e97d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zJvUwwHwyqCNTYd2kM8bWtRFYsDcJiGyROrhS1zTzPs20JsCQfohQcNkT1RuzxAIpvEfDB00s2U5Vqh0x96AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:40:09.828050Z","bundle_sha256":"43c4dc3481ce5b8c4866fced6fdfce1f96f9f523f60b2b931e43a51e988ce1d9"}}