{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4QI6SNEDVOGKOJQBPJMXEXR7NX","short_pith_number":"pith:4QI6SNED","canonical_record":{"source":{"id":"2310.13355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T08:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"5567a39a3315a430df6f78f0cb82e4ef3c5224cc5c849baf91b5f045273e95a6","abstract_canon_sha256":"6a3ab8ccbaeba7e4adc872095bd08b0ca2a1bf0b09a6349201bca74c3c2dc825"},"schema_version":"1.0"},"canonical_sha256":"e411e93483ab8ca726017a59725e3f6de192ed4f6d3e64367be4cb1ab9596a35","source":{"kind":"arxiv","id":"2310.13355","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13355","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13355v2","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13355","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"4QI6SNEDVOGK","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"4QI6SNEDVOGKOJQB","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"4QI6SNED","created_at":"2026-07-05T07:21:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4QI6SNEDVOGKOJQBPJMXEXR7NX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T08:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"5567a39a3315a430df6f78f0cb82e4ef3c5224cc5c849baf91b5f045273e95a6","abstract_canon_sha256":"6a3ab8ccbaeba7e4adc872095bd08b0ca2a1bf0b09a6349201bca74c3c2dc825"},"schema_version":"1.0"},"canonical_sha256":"e411e93483ab8ca726017a59725e3f6de192ed4f6d3e64367be4cb1ab9596a35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:28.478695Z","signature_b64":"5W2SDV+XqBtETEabnuDNJ/seYdrxJUhnthC9cW5MJvLH5U8MybcKD6DD+uvb2sPQ+qV/8hAVE8pX12XWkoseDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e411e93483ab8ca726017a59725e3f6de192ed4f6d3e64367be4cb1ab9596a35","last_reissued_at":"2026-07-05T07:21:28.478257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:28.478257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13355","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":"2026-07-05T07:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBWEohh/RBQAQZsGke3NyiDBo1NOZQrmJi2+paZ2CmFVbbQ1ZirAiNxnWkd4rti5shGX3TukUI9/6p8/DzepBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:55:07.968406Z"},"content_sha256":"0b4075f06515855dd32ca271b1edebf5b07d83d954b70cf55e746643b64ebc44","schema_version":"1.0","event_id":"sha256:0b4075f06515855dd32ca271b1edebf5b07d83d954b70cf55e746643b64ebc44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4QI6SNEDVOGKOJQBPJMXEXR7NX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SILC: Improving Vision Language Pretraining with Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Luc Van Gool, Lukas Hoyer, Muhammad Ferjad Naeem, Xiaohua Zhai, Yongqin Xian","submitted_at":"2023-10-20T08:44:47Z","abstract_excerpt":"Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contras"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13355","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/2310.13355/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":"2026-07-05T07:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvulmwsuWRKeSNxWMRDXKPOEeobhZH2MLrL4nKTkzCTXlLOf30rgLBTPiYpQnj4x7863UIr/09yE/2o+nB5cDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:55:07.968985Z"},"content_sha256":"217b0ce68780f86a08af4a31829fffe46c1d29da9c00e6697b8722f797992334","schema_version":"1.0","event_id":"sha256:217b0ce68780f86a08af4a31829fffe46c1d29da9c00e6697b8722f797992334"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/bundle.json","state_url":"https://pith.science/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/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":"2026-08-04T04:55:07Z","links":{"resolver":"https://pith.science/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX","bundle":"https://pith.science/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/bundle.json","state":"https://pith.science/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QI6SNEDVOGKOJQBPJMXEXR7NX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4QI6SNEDVOGKOJQBPJMXEXR7NX","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":"6a3ab8ccbaeba7e4adc872095bd08b0ca2a1bf0b09a6349201bca74c3c2dc825","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T08:44:47Z","title_canon_sha256":"5567a39a3315a430df6f78f0cb82e4ef3c5224cc5c849baf91b5f045273e95a6"},"schema_version":"1.0","source":{"id":"2310.13355","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13355","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13355v2","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13355","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"4QI6SNEDVOGK","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"4QI6SNEDVOGKOJQB","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"4QI6SNED","created_at":"2026-07-05T07:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:217b0ce68780f86a08af4a31829fffe46c1d29da9c00e6697b8722f797992334","target":"graph","created_at":"2026-07-05T07:21:28Z","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/2310.13355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contras","authors_text":"Federico Tombari, Luc Van Gool, Lukas Hoyer, Muhammad Ferjad Naeem, Xiaohua Zhai, Yongqin Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T08:44:47Z","title":"SILC: Improving Vision Language Pretraining with Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13355","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":"sha256:0b4075f06515855dd32ca271b1edebf5b07d83d954b70cf55e746643b64ebc44","target":"record","created_at":"2026-07-05T07:21:28Z","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":"6a3ab8ccbaeba7e4adc872095bd08b0ca2a1bf0b09a6349201bca74c3c2dc825","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T08:44:47Z","title_canon_sha256":"5567a39a3315a430df6f78f0cb82e4ef3c5224cc5c849baf91b5f045273e95a6"},"schema_version":"1.0","source":{"id":"2310.13355","kind":"arxiv","version":2}},"canonical_sha256":"e411e93483ab8ca726017a59725e3f6de192ed4f6d3e64367be4cb1ab9596a35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e411e93483ab8ca726017a59725e3f6de192ed4f6d3e64367be4cb1ab9596a35","first_computed_at":"2026-07-05T07:21:28.478257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:28.478257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5W2SDV+XqBtETEabnuDNJ/seYdrxJUhnthC9cW5MJvLH5U8MybcKD6DD+uvb2sPQ+qV/8hAVE8pX12XWkoseDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:28.478695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13355","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b4075f06515855dd32ca271b1edebf5b07d83d954b70cf55e746643b64ebc44","sha256:217b0ce68780f86a08af4a31829fffe46c1d29da9c00e6697b8722f797992334"],"state_sha256":"34fb1910e408316e7bfb10af85e238d8e68b12c665da0ed0cbfc3caf1225f1e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Osxv/OUirhww7iiogzpC6uN7QwEiNqg/qvCYqfs8L4qq/vY3lfFResFp/KPPTbWTYd5E7TW3u/iw/1zt+OEcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:55:07.974091Z","bundle_sha256":"787bd57f97da62b40f2b383c39108cdd25547da2001292be30a1866c609128df"}}