{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5WQRIDBZ2F7XA5W7V6NNJNUCDQ","short_pith_number":"pith:5WQRIDBZ","canonical_record":{"source":{"id":"2501.09608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-16T15:32:41Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"title_canon_sha256":"9a70477a73520439485bf62f5924f36f265a513aa7edbea34b1550a81c0ecf46","abstract_canon_sha256":"a0aee83e1837b28935b3540266dcca3c5305f334a7936f530c849b2efa20c463"},"schema_version":"1.0"},"canonical_sha256":"eda1140c39d17f7076dfaf9ad4b6821c0a61325fc91d64f15e130e22aa9ccda7","source":{"kind":"arxiv","id":"2501.09608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09608","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09608v1","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09608","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"5WQRIDBZ2F7X","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"5WQRIDBZ2F7XA5W7","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"5WQRIDBZ","created_at":"2026-07-05T10:01:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5WQRIDBZ2F7XA5W7V6NNJNUCDQ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-16T15:32:41Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"title_canon_sha256":"9a70477a73520439485bf62f5924f36f265a513aa7edbea34b1550a81c0ecf46","abstract_canon_sha256":"a0aee83e1837b28935b3540266dcca3c5305f334a7936f530c849b2efa20c463"},"schema_version":"1.0"},"canonical_sha256":"eda1140c39d17f7076dfaf9ad4b6821c0a61325fc91d64f15e130e22aa9ccda7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:49.677389Z","signature_b64":"daLjpPw+0UWr94ZzdwB6MxR+GnX+0BBEn39oSkKOgirkm8MpFygugngqq3m0MIZuRj5jKSLxLL+bxKyfWxe0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda1140c39d17f7076dfaf9ad4b6821c0a61325fc91d64f15e130e22aa9ccda7","last_reissued_at":"2026-07-05T10:01:49.676822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:49.676822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09608","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":"2026-07-05T10:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJQGUaUDyQXbND0lIjdU6854CHPw1Ru1ANKTI0LMNTp0qU+IpnmGj2dYoKwG1SaIqL0ek/ICWuJT0E368q9HAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:17:59.052507Z"},"content_sha256":"6c6d8a780f55e8f2a2a199d9a3f5a3027b2f87113b4475aa52b510000ee5e7d8","schema_version":"1.0","event_id":"sha256:6c6d8a780f55e8f2a2a199d9a3f5a3027b2f87113b4475aa52b510000ee5e7d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5WQRIDBZ2F7XA5W7V6NNJNUCDQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Donghuo Zeng, Kazushi Ikeda","submitted_at":"2025-01-16T15:32:41Z","abstract_excerpt":"Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where representations of different modalities, such as audio and visual data, are aligned based on annotated labels. This approach tends to underutilize latent complex features and potential relationships inherent in the distributions of audio and visual data that are not directly tied to the labels, resulting in suboptimal performance in audio-visual embedding learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09608","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/2501.09608/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":"2026-07-05T10:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMfoehnjBHZdiWJo+Aa+VCL02dK0hxLknCWE55UITZknMJUrHSprL+jXDt+7AT6vs9xWl5J4QbyClKb4bAgOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:17:59.053053Z"},"content_sha256":"6082480c937f5e27cb6669c03b26f91d98b6dd60f1f21c4cf3d72e991d702a27","schema_version":"1.0","event_id":"sha256:6082480c937f5e27cb6669c03b26f91d98b6dd60f1f21c4cf3d72e991d702a27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/bundle.json","state_url":"https://pith.science/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/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":"2026-08-12T06:17:59Z","links":{"resolver":"https://pith.science/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ","bundle":"https://pith.science/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/bundle.json","state":"https://pith.science/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WQRIDBZ2F7XA5W7V6NNJNUCDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5WQRIDBZ2F7XA5W7V6NNJNUCDQ","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":"a0aee83e1837b28935b3540266dcca3c5305f334a7936f530c849b2efa20c463","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-16T15:32:41Z","title_canon_sha256":"9a70477a73520439485bf62f5924f36f265a513aa7edbea34b1550a81c0ecf46"},"schema_version":"1.0","source":{"id":"2501.09608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09608","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09608v1","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09608","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"5WQRIDBZ2F7X","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"5WQRIDBZ2F7XA5W7","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"5WQRIDBZ","created_at":"2026-07-05T10:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:6082480c937f5e27cb6669c03b26f91d98b6dd60f1f21c4cf3d72e991d702a27","target":"graph","created_at":"2026-07-05T10:01:49Z","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/2501.09608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where representations of different modalities, such as audio and visual data, are aligned based on annotated labels. This approach tends to underutilize latent complex features and potential relationships inherent in the distributions of audio and visual data that are not directly tied to the labels, resulting in suboptimal performance in audio-visual embedding learnin","authors_text":"Donghuo Zeng, Kazushi Ikeda","cross_cats":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-16T15:32:41Z","title":"Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09608","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":"sha256:6c6d8a780f55e8f2a2a199d9a3f5a3027b2f87113b4475aa52b510000ee5e7d8","target":"record","created_at":"2026-07-05T10:01:49Z","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":"a0aee83e1837b28935b3540266dcca3c5305f334a7936f530c849b2efa20c463","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-16T15:32:41Z","title_canon_sha256":"9a70477a73520439485bf62f5924f36f265a513aa7edbea34b1550a81c0ecf46"},"schema_version":"1.0","source":{"id":"2501.09608","kind":"arxiv","version":1}},"canonical_sha256":"eda1140c39d17f7076dfaf9ad4b6821c0a61325fc91d64f15e130e22aa9ccda7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eda1140c39d17f7076dfaf9ad4b6821c0a61325fc91d64f15e130e22aa9ccda7","first_computed_at":"2026-07-05T10:01:49.676822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:49.676822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"daLjpPw+0UWr94ZzdwB6MxR+GnX+0BBEn39oSkKOgirkm8MpFygugngqq3m0MIZuRj5jKSLxLL+bxKyfWxe0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:49.677389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c6d8a780f55e8f2a2a199d9a3f5a3027b2f87113b4475aa52b510000ee5e7d8","sha256:6082480c937f5e27cb6669c03b26f91d98b6dd60f1f21c4cf3d72e991d702a27"],"state_sha256":"f713f4f8dd7267818a9a33607be79e13f72b1115023fb76152febfbfdbc89c7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqaQ+4HfvCQf7i9dZpcRARwexGFqofR54i2LtJXwDmjG8pCwEVbW6vsngrkcn5B4pZOykwjbNbbTrfBGE4QgDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:17:59.062050Z","bundle_sha256":"809dbb7a142a4630c1860e39f8066c4eef9db264720b680208f9cbc8e2f60c51"}}