{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6AJYNVTBNN5LWTYQ7WWTUHTWKC","short_pith_number":"pith:6AJYNVTB","canonical_record":{"source":{"id":"2104.06401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"70ceff54c49319c7f10855ab030dbdf0abae0c54cfaf79722b4b2aba309fb612","abstract_canon_sha256":"4054e00254f28dbc9441fbbb0daf8a525d0c5e678c0936a1adb3527ce975db8a"},"schema_version":"1.0"},"canonical_sha256":"f01386d6616b7abb4f10fdad3a1e765086641966ac7055e290614a1a7167edf5","source":{"kind":"arxiv","id":"2104.06401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06401","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06401v2","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06401","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"6AJYNVTBNN5L","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"6AJYNVTBNN5LWTYQ","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"6AJYNVTB","created_at":"2026-07-05T04:38:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6AJYNVTBNN5LWTYQ7WWTUHTWKC","target":"record","payload":{"canonical_record":{"source":{"id":"2104.06401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"70ceff54c49319c7f10855ab030dbdf0abae0c54cfaf79722b4b2aba309fb612","abstract_canon_sha256":"4054e00254f28dbc9441fbbb0daf8a525d0c5e678c0936a1adb3527ce975db8a"},"schema_version":"1.0"},"canonical_sha256":"f01386d6616b7abb4f10fdad3a1e765086641966ac7055e290614a1a7167edf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:42.445228Z","signature_b64":"sEoYnXqugZQXz44Oc9cVjB59dvkCCtMGnvJ0wcYPeDAK6M/OGbsrARQeCzrsd8XnGvfzJFxuonSwGb/G3WAwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01386d6616b7abb4f10fdad3a1e765086641966ac7055e290614a1a7167edf5","last_reissued_at":"2026-07-05T04:38:42.444875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:42.444875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.06401","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKGGWGRRyO0y/tscX8fUd5HwiOtPL5sgg4ALtmd+SFQ0HESOHSreA7K95kjQvQPtsxhrhW0i8nvbtrNIoD5tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:12.690190Z"},"content_sha256":"dbee879bf308788428f444e4887472b945bd0d378ae7a3fd1695c9e578a7949c","schema_version":"1.0","event_id":"sha256:dbee879bf308788428f444e4887472b945bd0d378ae7a3fd1695c9e578a7949c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6AJYNVTBNN5LWTYQ7WWTUHTWKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised object detection from audio-visual correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Florian Metze, Francois Fagan, Triantafyllos Afouras, Yuki M. Asano","submitted_at":"2021-04-13T17:59:03Z","abstract_excerpt":"We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using the audio component to \"teach\" the object detector. While this problem is related to sound source localisation, it is considerably harder because the detector must classify the objects by type, enumerate each instance of the object, and do so even when the object is silent. We tackle this problem by first designing a self-supervised framework with a contrasti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06401","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.06401/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":"2026-07-05T04:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RqGwZQlOSTWAJoGu1ychDKbrtH0c2+W3rPV+Wk+7qvoK57ZEr2TI0/4DwR5EzfGwI17Q3h4hiCwT2U0wJo09AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:12.690596Z"},"content_sha256":"cfb6e5b5ed02c96e56e7a5edb1b6f1b86f47d85dadfc900f664510946d5364ac","schema_version":"1.0","event_id":"sha256:cfb6e5b5ed02c96e56e7a5edb1b6f1b86f47d85dadfc900f664510946d5364ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/bundle.json","state_url":"https://pith.science/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/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":"2026-07-07T13:51:12Z","links":{"resolver":"https://pith.science/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC","bundle":"https://pith.science/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/bundle.json","state":"https://pith.science/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6AJYNVTBNN5LWTYQ7WWTUHTWKC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6AJYNVTBNN5LWTYQ7WWTUHTWKC","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":"4054e00254f28dbc9441fbbb0daf8a525d0c5e678c0936a1adb3527ce975db8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:03Z","title_canon_sha256":"70ceff54c49319c7f10855ab030dbdf0abae0c54cfaf79722b4b2aba309fb612"},"schema_version":"1.0","source":{"id":"2104.06401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06401","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06401v2","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06401","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"6AJYNVTBNN5L","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"6AJYNVTBNN5LWTYQ","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"6AJYNVTB","created_at":"2026-07-05T04:38:42Z"}],"graph_snapshots":[{"event_id":"sha256:cfb6e5b5ed02c96e56e7a5edb1b6f1b86f47d85dadfc900f664510946d5364ac","target":"graph","created_at":"2026-07-05T04:38:42Z","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/2104.06401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using the audio component to \"teach\" the object detector. While this problem is related to sound source localisation, it is considerably harder because the detector must classify the objects by type, enumerate each instance of the object, and do so even when the object is silent. We tackle this problem by first designing a self-supervised framework with a contrasti","authors_text":"Andrea Vedaldi, Florian Metze, Francois Fagan, Triantafyllos Afouras, Yuki M. Asano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:03Z","title":"Self-supervised object detection from audio-visual correspondence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06401","kind":"arxiv","version":2},"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:dbee879bf308788428f444e4887472b945bd0d378ae7a3fd1695c9e578a7949c","target":"record","created_at":"2026-07-05T04:38:42Z","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":"4054e00254f28dbc9441fbbb0daf8a525d0c5e678c0936a1adb3527ce975db8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:03Z","title_canon_sha256":"70ceff54c49319c7f10855ab030dbdf0abae0c54cfaf79722b4b2aba309fb612"},"schema_version":"1.0","source":{"id":"2104.06401","kind":"arxiv","version":2}},"canonical_sha256":"f01386d6616b7abb4f10fdad3a1e765086641966ac7055e290614a1a7167edf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f01386d6616b7abb4f10fdad3a1e765086641966ac7055e290614a1a7167edf5","first_computed_at":"2026-07-05T04:38:42.444875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:42.444875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sEoYnXqugZQXz44Oc9cVjB59dvkCCtMGnvJ0wcYPeDAK6M/OGbsrARQeCzrsd8XnGvfzJFxuonSwGb/G3WAwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:42.445228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbee879bf308788428f444e4887472b945bd0d378ae7a3fd1695c9e578a7949c","sha256:cfb6e5b5ed02c96e56e7a5edb1b6f1b86f47d85dadfc900f664510946d5364ac"],"state_sha256":"274c8ef20a4884d3969f2b2a7a7cd3afef527c7e0a1774fc77f98753b1317503"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKhbbQr3vDktd72qShR4mEYbdRxP8oGg57YqY5wA9FoZx7+KligozPA2T0usBc1JtPo/sZwv83LvB6Ts9COJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:51:12.692629Z","bundle_sha256":"b5fd11a806cee8fad82bdbec6c32c2e52f25d343dabfddf78b7b4a9e7af881cf"}}