{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBG5NRRPPNM62KR7JQ6PQOL4OU","short_pith_number":"pith:BBG5NRRP","schema_version":"1.0","canonical_sha256":"084dd6c62f7b59ed2a3f4c3cf8397c753aff75410cb144f1df7a32625ee147f3","source":{"kind":"arxiv","id":"2508.08644","version":1},"attestation_state":"computed","paper":{"title":"AME: Aligned Manifold Entropy for Robust Vision-Language Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guiming Cao, Yuming Ou","submitted_at":"2025-08-12T05:16:00Z","abstract_excerpt":"Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entangle"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.08644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T05:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"2dec354d11772fe6ab41f74b4c923bc09bff436c15bf18ef09abcabf72d7debd","abstract_canon_sha256":"e0d6b9408cae798ce23d46e8f8ecb764ae36e48c98b373f0066dfeee4a102668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:31.775784Z","signature_b64":"0tk1X8/5Kqixc9jRpsaF4g2WrIPgQYgVOG00pp6Kuk7vVVkoByp96V8MCvsWeIJIpBsr6TXS7nzJ0axPdt6sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084dd6c62f7b59ed2a3f4c3cf8397c753aff75410cb144f1df7a32625ee147f3","last_reissued_at":"2026-07-05T11:52:31.775255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:31.775255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AME: Aligned Manifold Entropy for Robust Vision-Language Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guiming Cao, Yuming Ou","submitted_at":"2025-08-12T05:16:00Z","abstract_excerpt":"Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entangle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08644","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/2508.08644/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.08644","created_at":"2026-07-05T11:52:31.775325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08644v1","created_at":"2026-07-05T11:52:31.775325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08644","created_at":"2026-07-05T11:52:31.775325+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBG5NRRPPNM6","created_at":"2026-07-05T11:52:31.775325+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBG5NRRPPNM62KR7","created_at":"2026-07-05T11:52:31.775325+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBG5NRRP","created_at":"2026-07-05T11:52:31.775325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU","json":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU.json","graph_json":"https://pith.science/api/pith-number/BBG5NRRPPNM62KR7JQ6PQOL4OU/graph.json","events_json":"https://pith.science/api/pith-number/BBG5NRRPPNM62KR7JQ6PQOL4OU/events.json","paper":"https://pith.science/paper/BBG5NRRP"},"agent_actions":{"view_html":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU","download_json":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU.json","view_paper":"https://pith.science/paper/BBG5NRRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08644&json=true","fetch_graph":"https://pith.science/api/pith-number/BBG5NRRPPNM62KR7JQ6PQOL4OU/graph.json","fetch_events":"https://pith.science/api/pith-number/BBG5NRRPPNM62KR7JQ6PQOL4OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU/action/storage_attestation","attest_author":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU/action/author_attestation","sign_citation":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU/action/citation_signature","submit_replication":"https://pith.science/pith/BBG5NRRPPNM62KR7JQ6PQOL4OU/action/replication_record"}},"created_at":"2026-07-05T11:52:31.775325+00:00","updated_at":"2026-07-05T11:52:31.775325+00:00"}