{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HSLEWGFRKIXLYAYO42BMKEBPTX","short_pith_number":"pith:HSLEWGFR","canonical_record":{"source":{"id":"2206.12772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T03:00:02Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"725f689fa678b5e6ad652001d6bb1de6737e43d8605e65433b0b346fd0faf38b","abstract_canon_sha256":"a271636660cb9af7be0d5e3725b92a2479998401c45d31df2b5d2dcc4bb35c2b"},"schema_version":"1.0"},"canonical_sha256":"3c964b18b1522ebc030ee682c5102f9df1a2a41311270faa86f9eb2d29914ba9","source":{"kind":"arxiv","id":"2206.12772","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12772","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12772v2","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12772","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"HSLEWGFRKIXL","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"HSLEWGFRKIXLYAYO","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"HSLEWGFR","created_at":"2026-07-05T04:48:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HSLEWGFRKIXLYAYO42BMKEBPTX","target":"record","payload":{"canonical_record":{"source":{"id":"2206.12772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T03:00:02Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"725f689fa678b5e6ad652001d6bb1de6737e43d8605e65433b0b346fd0faf38b","abstract_canon_sha256":"a271636660cb9af7be0d5e3725b92a2479998401c45d31df2b5d2dcc4bb35c2b"},"schema_version":"1.0"},"canonical_sha256":"3c964b18b1522ebc030ee682c5102f9df1a2a41311270faa86f9eb2d29914ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:14.121210Z","signature_b64":"uZfLGo4LjQ1ZUmeFax09cYCuYr0ZvdCmMvD/ZOIdzXCYmLI2GE8U3TcOIM5PneDZ0hjJrPDSfYTmpfpBN5MNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c964b18b1522ebc030ee682c5102f9df1a2a41311270faa86f9eb2d29914ba9","last_reissued_at":"2026-07-05T04:48:14.120730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:14.120730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.12772","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":"2026-07-05T04:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C04uMzr69Nwkzm3nNw5IVaRlo/YguMdr73bCPxL0Z9Og8mevZO86TbZWLZGv/wih/lwPonivauBVBsCVQgyhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:50.822275Z"},"content_sha256":"c28d8d0d5baa566893360812ad502f6ee06946e01b291071ed8c08a973456630","schema_version":"1.0","event_id":"sha256:c28d8d0d5baa566893360812ad502f6ee06946e01b291071ed8c08a973456630"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HSLEWGFRKIXLYAYO42BMKEBPTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chen Ju, Jinxiang Liu, Weidi Xie, Ya Zhang","submitted_at":"2022-06-26T03:00:02Z","abstract_excerpt":"We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the effects of data augmentations, and reveal that (1) composition of data augmentations plays a critical role, i.e. explicitly encouraging the audio-visual representations to be invariant to various transformations~({\\em transformation invariance}); (2) enforcing geometric consistency substantially improves the quality of learned representations, i.e. the detected "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12772","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/2206.12772/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":"2026-07-05T04:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snikz6UoRyRre9juIElF6TQX2AUaMN0xaQ3hNd3sssYLEwLnPrID3gJZAa+xXcMK8hTzVvzCOhO+n8VVWeAfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:50.822680Z"},"content_sha256":"a3ea438334188d21ee4090ee8df8fc4231979b6a1af4c8e63c4093badd674455","schema_version":"1.0","event_id":"sha256:a3ea438334188d21ee4090ee8df8fc4231979b6a1af4c8e63c4093badd674455"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/bundle.json","state_url":"https://pith.science/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/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":"2026-07-07T07:17:50Z","links":{"resolver":"https://pith.science/pith/HSLEWGFRKIXLYAYO42BMKEBPTX","bundle":"https://pith.science/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/bundle.json","state":"https://pith.science/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSLEWGFRKIXLYAYO42BMKEBPTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HSLEWGFRKIXLYAYO42BMKEBPTX","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":"a271636660cb9af7be0d5e3725b92a2479998401c45d31df2b5d2dcc4bb35c2b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T03:00:02Z","title_canon_sha256":"725f689fa678b5e6ad652001d6bb1de6737e43d8605e65433b0b346fd0faf38b"},"schema_version":"1.0","source":{"id":"2206.12772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12772","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12772v2","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12772","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"HSLEWGFRKIXL","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"HSLEWGFRKIXLYAYO","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"HSLEWGFR","created_at":"2026-07-05T04:48:14Z"}],"graph_snapshots":[{"event_id":"sha256:a3ea438334188d21ee4090ee8df8fc4231979b6a1af4c8e63c4093badd674455","target":"graph","created_at":"2026-07-05T04:48:14Z","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/2206.12772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the effects of data augmentations, and reveal that (1) composition of data augmentations plays a critical role, i.e. explicitly encouraging the audio-visual representations to be invariant to various transformations~({\\em transformation invariance}); (2) enforcing geometric consistency substantially improves the quality of learned representations, i.e. the detected ","authors_text":"Chen Ju, Jinxiang Liu, Weidi Xie, Ya Zhang","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T03:00:02Z","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12772","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:c28d8d0d5baa566893360812ad502f6ee06946e01b291071ed8c08a973456630","target":"record","created_at":"2026-07-05T04:48:14Z","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":"a271636660cb9af7be0d5e3725b92a2479998401c45d31df2b5d2dcc4bb35c2b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T03:00:02Z","title_canon_sha256":"725f689fa678b5e6ad652001d6bb1de6737e43d8605e65433b0b346fd0faf38b"},"schema_version":"1.0","source":{"id":"2206.12772","kind":"arxiv","version":2}},"canonical_sha256":"3c964b18b1522ebc030ee682c5102f9df1a2a41311270faa86f9eb2d29914ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c964b18b1522ebc030ee682c5102f9df1a2a41311270faa86f9eb2d29914ba9","first_computed_at":"2026-07-05T04:48:14.120730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:14.120730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uZfLGo4LjQ1ZUmeFax09cYCuYr0ZvdCmMvD/ZOIdzXCYmLI2GE8U3TcOIM5PneDZ0hjJrPDSfYTmpfpBN5MNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:14.121210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c28d8d0d5baa566893360812ad502f6ee06946e01b291071ed8c08a973456630","sha256:a3ea438334188d21ee4090ee8df8fc4231979b6a1af4c8e63c4093badd674455"],"state_sha256":"d98c437a3f21556340be7292a23d9be25e54339cf374d2540a98fecf0febad8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQCQ1wOtYa/bFiIMZkzfbxraonaKcWiDoAuU1Bd4sItQMrKeNcsOJeq1g0KdrYd8SIR8ZcVv/a4IRDjKtKZQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:17:50.824834Z","bundle_sha256":"5a9f2c608a10765c597e452789ec534a93b9886a68203c11dad4ffabf1ffc382"}}