{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:42UVKZBRVVIYEF3QUP2PTGT77D","short_pith_number":"pith:42UVKZBR","canonical_record":{"source":{"id":"2507.17368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T10:04:30Z","cross_cats_sorted":[],"title_canon_sha256":"7767f1259a166c00f77e31883f86f6acda96ea8d84398d59173405ce36903c7e","abstract_canon_sha256":"ecb6b4ee2317df3aa181ce971d50d666ebdada5a6b3db46c5e9f603089cbb8ac"},"schema_version":"1.0"},"canonical_sha256":"e6a9556431ad51821770a3f4f99a7ff8d9e0767d0c2890f94fc5c0d7b5349ff5","source":{"kind":"arxiv","id":"2507.17368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17368","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17368v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17368","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"42UVKZBRVVIY","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"42UVKZBRVVIYEF3Q","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"42UVKZBR","created_at":"2026-07-05T11:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:42UVKZBRVVIYEF3QUP2PTGT77D","target":"record","payload":{"canonical_record":{"source":{"id":"2507.17368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T10:04:30Z","cross_cats_sorted":[],"title_canon_sha256":"7767f1259a166c00f77e31883f86f6acda96ea8d84398d59173405ce36903c7e","abstract_canon_sha256":"ecb6b4ee2317df3aa181ce971d50d666ebdada5a6b3db46c5e9f603089cbb8ac"},"schema_version":"1.0"},"canonical_sha256":"e6a9556431ad51821770a3f4f99a7ff8d9e0767d0c2890f94fc5c0d7b5349ff5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:06.369463Z","signature_b64":"O3YknFvBe0npB5bO3UZhynH69TMxwO5GkMy8fQ+0EgYUMHJcS3NRirOvKRxbfSiL8CKtF+iLmAXzfFoTJFoZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a9556431ad51821770a3f4f99a7ff8d9e0767d0c2890f94fc5c0d7b5349ff5","last_reissued_at":"2026-07-05T11:42:06.368893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:06.368893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.17368","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":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mxLuLnRld5c+Y9puJkMgPsukA36VTmrQe8ZnqjURimJSSCPgqDWTRp3cftvNpuG06ovnQUj85xhE89WKKEzbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:36:12.220572Z"},"content_sha256":"473befbd430e2bb8950ae047df0cb898b542c6a29c96274b92198f4357e3e552","schema_version":"1.0","event_id":"sha256:473befbd430e2bb8950ae047df0cb898b542c6a29c96274b92198f4357e3e552"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:42UVKZBRVVIYEF3QUP2PTGT77D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chong Tang, Hao Dai, Jagmohan Chauhan","submitted_at":"2025-07-23T10:04:30Z","abstract_excerpt":"Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-tailed learning. First, we model class-conditional distributions via a Variational Autoencoder to miti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17368","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/2507.17368/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":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTF0anU3gtSmNuVYxYRxAb0ewCu1JFBcznDaaF/LoeW0JyK29+bpjMT7KhENurAxCm1tkisd5H300TufSf7aAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:36:12.221249Z"},"content_sha256":"acda06f4e00bf734a2b8f2ed059e5ee55140e8ec714a71b28d147279081369d6","schema_version":"1.0","event_id":"sha256:acda06f4e00bf734a2b8f2ed059e5ee55140e8ec714a71b28d147279081369d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42UVKZBRVVIYEF3QUP2PTGT77D/bundle.json","state_url":"https://pith.science/pith/42UVKZBRVVIYEF3QUP2PTGT77D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42UVKZBRVVIYEF3QUP2PTGT77D/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":"2026-08-14T09:36:12Z","links":{"resolver":"https://pith.science/pith/42UVKZBRVVIYEF3QUP2PTGT77D","bundle":"https://pith.science/pith/42UVKZBRVVIYEF3QUP2PTGT77D/bundle.json","state":"https://pith.science/pith/42UVKZBRVVIYEF3QUP2PTGT77D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42UVKZBRVVIYEF3QUP2PTGT77D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:42UVKZBRVVIYEF3QUP2PTGT77D","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":"ecb6b4ee2317df3aa181ce971d50d666ebdada5a6b3db46c5e9f603089cbb8ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T10:04:30Z","title_canon_sha256":"7767f1259a166c00f77e31883f86f6acda96ea8d84398d59173405ce36903c7e"},"schema_version":"1.0","source":{"id":"2507.17368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17368","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17368v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17368","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"42UVKZBRVVIY","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"42UVKZBRVVIYEF3Q","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"42UVKZBR","created_at":"2026-07-05T11:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:acda06f4e00bf734a2b8f2ed059e5ee55140e8ec714a71b28d147279081369d6","target":"graph","created_at":"2026-07-05T11:42:06Z","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/2507.17368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-tailed learning. First, we model class-conditional distributions via a Variational Autoencoder to miti","authors_text":"Chong Tang, Hao Dai, Jagmohan Chauhan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T10:04:30Z","title":"ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17368","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":"sha256:473befbd430e2bb8950ae047df0cb898b542c6a29c96274b92198f4357e3e552","target":"record","created_at":"2026-07-05T11:42:06Z","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":"ecb6b4ee2317df3aa181ce971d50d666ebdada5a6b3db46c5e9f603089cbb8ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T10:04:30Z","title_canon_sha256":"7767f1259a166c00f77e31883f86f6acda96ea8d84398d59173405ce36903c7e"},"schema_version":"1.0","source":{"id":"2507.17368","kind":"arxiv","version":1}},"canonical_sha256":"e6a9556431ad51821770a3f4f99a7ff8d9e0767d0c2890f94fc5c0d7b5349ff5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6a9556431ad51821770a3f4f99a7ff8d9e0767d0c2890f94fc5c0d7b5349ff5","first_computed_at":"2026-07-05T11:42:06.368893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:06.368893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O3YknFvBe0npB5bO3UZhynH69TMxwO5GkMy8fQ+0EgYUMHJcS3NRirOvKRxbfSiL8CKtF+iLmAXzfFoTJFoZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:06.369463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:473befbd430e2bb8950ae047df0cb898b542c6a29c96274b92198f4357e3e552","sha256:acda06f4e00bf734a2b8f2ed059e5ee55140e8ec714a71b28d147279081369d6"],"state_sha256":"e6f6630c3db6f2ee36824c6d9e09a78151014c86d5668833536a28e398053e08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmNv8R8iJNZ1wrNyGLQKLsKXC11zF5AxV2jmFuy0y1dT6tfOefx+7gk0FB6XkftIu9QPBoWu+jYtg/GDaRGKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:36:12.226814Z","bundle_sha256":"85900a1fca7dc42f91491cdec111ddad18e174fc6b22129a1fdc398b630efcb4"}}