{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LMM2PCOODLSIJTUT6CIDV4GS53","short_pith_number":"pith:LMM2PCOO","canonical_record":{"source":{"id":"2312.11938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:31:30Z","cross_cats_sorted":[],"title_canon_sha256":"b4377d58690b700c150cd99e0a33854335a9dc03e8e0f91f560e545b7395a717","abstract_canon_sha256":"54530119c02ddb5b068ac68085ba3dce42e727cc66478f408d250ccd838ccf77"},"schema_version":"1.0"},"canonical_sha256":"5b19a789ce1ae484ce93f0903af0d2eec600a43843bc04ba44a93aa02ee5fdc8","source":{"kind":"arxiv","id":"2312.11938","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11938","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11938v1","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11938","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"LMM2PCOODLSI","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"LMM2PCOODLSIJTUT","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"LMM2PCOO","created_at":"2026-07-05T07:25:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LMM2PCOODLSIJTUT6CIDV4GS53","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:31:30Z","cross_cats_sorted":[],"title_canon_sha256":"b4377d58690b700c150cd99e0a33854335a9dc03e8e0f91f560e545b7395a717","abstract_canon_sha256":"54530119c02ddb5b068ac68085ba3dce42e727cc66478f408d250ccd838ccf77"},"schema_version":"1.0"},"canonical_sha256":"5b19a789ce1ae484ce93f0903af0d2eec600a43843bc04ba44a93aa02ee5fdc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:56.843184Z","signature_b64":"H65k8s+QEvUa5c+0s+zzUZimAdsvqqAum1M7LGrEIjECN0YkcOvj3zJrkCiUbjQM+vtYTHyodwhLPYU4XkyJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b19a789ce1ae484ce93f0903af0d2eec600a43843bc04ba44a93aa02ee5fdc8","last_reissued_at":"2026-07-05T07:25:56.842752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:56.842752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11938","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":"2026-07-05T07:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+RR6rydY22UTjIl57DlsjVM+urH3TE4yBMbsbAMnoI4dECwJXUBJqxvwWkaWiGBYjfLyDezn3M+NzcQpPVhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:43:04.181963Z"},"content_sha256":"b4cbd87083935c43bb3fe9b60c64b027a9af3fbe5ffe91907f1f531fd7c4a07b","schema_version":"1.0","event_id":"sha256:b4cbd87083935c43bb3fe9b60c64b027a9af3fbe5ffe91907f1f531fd7c4a07b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LMM2PCOODLSIJTUT6CIDV4GS53","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DMT: Comprehensive Distillation with Multiple Self-supervised Teachers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Wang, Jing Wang, Jun Wang, Qiang Zhou, Wei Zhang, Yuang Liu","submitted_at":"2023-12-19T08:31:30Z","abstract_excerpt":"Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained within their specific framework alone, failing to consider the complementary nature of visual representations. To tackle this issue, we introduce Comprehensive Distillation with Multiple Self-supervised Teachers (DMT) for pretrained model compression, which leverages the strengths of multiple off-the-shelf self-supervised models. Our experimental results on promi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11938","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/2312.11938/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":"2026-07-05T07:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nLhd2r7E8PrvPiqdd0AqNqUXXphbsAWJpcO8btJLYG5j/ljzC1JGKe/MjQPPgWXtsg1YIpU3AvANu4krFRgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:43:04.182345Z"},"content_sha256":"b6e186145d93e4a9d29cc2759a071c2fc795d90e370257db1a8c3dcb6e458237","schema_version":"1.0","event_id":"sha256:b6e186145d93e4a9d29cc2759a071c2fc795d90e370257db1a8c3dcb6e458237"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMM2PCOODLSIJTUT6CIDV4GS53/bundle.json","state_url":"https://pith.science/pith/LMM2PCOODLSIJTUT6CIDV4GS53/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMM2PCOODLSIJTUT6CIDV4GS53/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":"2026-07-06T13:43:04Z","links":{"resolver":"https://pith.science/pith/LMM2PCOODLSIJTUT6CIDV4GS53","bundle":"https://pith.science/pith/LMM2PCOODLSIJTUT6CIDV4GS53/bundle.json","state":"https://pith.science/pith/LMM2PCOODLSIJTUT6CIDV4GS53/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMM2PCOODLSIJTUT6CIDV4GS53/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LMM2PCOODLSIJTUT6CIDV4GS53","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":"54530119c02ddb5b068ac68085ba3dce42e727cc66478f408d250ccd838ccf77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:31:30Z","title_canon_sha256":"b4377d58690b700c150cd99e0a33854335a9dc03e8e0f91f560e545b7395a717"},"schema_version":"1.0","source":{"id":"2312.11938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11938","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11938v1","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11938","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"LMM2PCOODLSI","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"LMM2PCOODLSIJTUT","created_at":"2026-07-05T07:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"LMM2PCOO","created_at":"2026-07-05T07:25:56Z"}],"graph_snapshots":[{"event_id":"sha256:b6e186145d93e4a9d29cc2759a071c2fc795d90e370257db1a8c3dcb6e458237","target":"graph","created_at":"2026-07-05T07:25:56Z","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/2312.11938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained within their specific framework alone, failing to consider the complementary nature of visual representations. To tackle this issue, we introduce Comprehensive Distillation with Multiple Self-supervised Teachers (DMT) for pretrained model compression, which leverages the strengths of multiple off-the-shelf self-supervised models. Our experimental results on promi","authors_text":"Fan Wang, Jing Wang, Jun Wang, Qiang Zhou, Wei Zhang, Yuang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:31:30Z","title":"DMT: Comprehensive Distillation with Multiple Self-supervised Teachers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11938","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:b4cbd87083935c43bb3fe9b60c64b027a9af3fbe5ffe91907f1f531fd7c4a07b","target":"record","created_at":"2026-07-05T07:25:56Z","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":"54530119c02ddb5b068ac68085ba3dce42e727cc66478f408d250ccd838ccf77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:31:30Z","title_canon_sha256":"b4377d58690b700c150cd99e0a33854335a9dc03e8e0f91f560e545b7395a717"},"schema_version":"1.0","source":{"id":"2312.11938","kind":"arxiv","version":1}},"canonical_sha256":"5b19a789ce1ae484ce93f0903af0d2eec600a43843bc04ba44a93aa02ee5fdc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b19a789ce1ae484ce93f0903af0d2eec600a43843bc04ba44a93aa02ee5fdc8","first_computed_at":"2026-07-05T07:25:56.842752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:56.842752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H65k8s+QEvUa5c+0s+zzUZimAdsvqqAum1M7LGrEIjECN0YkcOvj3zJrkCiUbjQM+vtYTHyodwhLPYU4XkyJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:56.843184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4cbd87083935c43bb3fe9b60c64b027a9af3fbe5ffe91907f1f531fd7c4a07b","sha256:b6e186145d93e4a9d29cc2759a071c2fc795d90e370257db1a8c3dcb6e458237"],"state_sha256":"7c59ca0de121afcbb1c95e329e61e2d212de49786e8a17e58e371d1707928c80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLQR2WC2ESJ55568SIIurPrcUVUbw60s8AW/bm6pGre65ixx15/iXisHl6cOsVHIAsh4BxiAomz/9xZdUWzqDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:43:04.184342Z","bundle_sha256":"5ad26aacbcc95533640cad8e91f29820d1075513841b360d5c071bf6da5673fb"}}