{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QP6IQ4DKVM34CYF4L2FXZ2LVTP","short_pith_number":"pith:QP6IQ4DK","canonical_record":{"source":{"id":"2208.13628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T14:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f54ea78615128859bfd35d59465e4d7b541ee118479ee607c4d544dfbf6d07b6","abstract_canon_sha256":"f3596aa8574c2793ab43e46ea81e1eb4863792260a67cb9d3750d0184dede2e4"},"schema_version":"1.0"},"canonical_sha256":"83fc88706aab37c160bc5e8b7ce9759be698c7655195963da765dbbd3287c200","source":{"kind":"arxiv","id":"2208.13628","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.13628","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2208.13628v2","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13628","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"QP6IQ4DKVM34","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"QP6IQ4DKVM34CYF4","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"QP6IQ4DK","created_at":"2026-07-05T05:03:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QP6IQ4DKVM34CYF4L2FXZ2LVTP","target":"record","payload":{"canonical_record":{"source":{"id":"2208.13628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T14:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f54ea78615128859bfd35d59465e4d7b541ee118479ee607c4d544dfbf6d07b6","abstract_canon_sha256":"f3596aa8574c2793ab43e46ea81e1eb4863792260a67cb9d3750d0184dede2e4"},"schema_version":"1.0"},"canonical_sha256":"83fc88706aab37c160bc5e8b7ce9759be698c7655195963da765dbbd3287c200","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:39.183299Z","signature_b64":"Q323C7p4F8zRO9rfeBlrIjTFz6rUW/ejeX1/MDNvt62O6s0S4OV+NxmnasMKRbi+6azXViac5uM6LJa4X7sOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83fc88706aab37c160bc5e8b7ce9759be698c7655195963da765dbbd3287c200","last_reissued_at":"2026-07-05T05:03:39.182962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:39.182962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.13628","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":"2026-07-05T05:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/VMZT21SLKtQop4bpA/Y7PSYthd6TQGBKnmbC8ot8onYlj9f1wOpDfgPRD8jinIIHo9ryrjp7Ys2fD7mJTubCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:45:56.800701Z"},"content_sha256":"ec22e2f8fee73fd2d685a6ecbfde48637ecc657ba036126e9e5965e96de07c28","schema_version":"1.0","event_id":"sha256:ec22e2f8fee73fd2d685a6ecbfde48637ecc657ba036126e9e5965e96de07c28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QP6IQ4DKVM34CYF4L2FXZ2LVTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guillaume Couairon, Matthieu Cord, Mustafa Shukor","submitted_at":"2022-08-29T14:24:08Z","abstract_excerpt":"Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks. The current trend is to move towards ever larger models and pretraining datasets. This computational headlong rush does not seem reasonable in the long term to move toward sustainable solutions, and de facto excludes academic laboratories with limited resources. In this work, we propose a new framework, dubbed ViCHA, that efficiently exploits the input data to boost the learning by: (a) a new hierarchical cross-modal alignment loss, (b) new self-supervised scheme based on masked image mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13628","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/2208.13628/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":"2026-07-05T05:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWh7VvMhjzcmab8s6wc0/62Pf/P+NPTyM+dYzLNqIEJDEJiqCmOHcz+k6a7nWOIymryTn06/FM9CrUC9HpGoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:45:56.801082Z"},"content_sha256":"cacb1bf7220e7d483fe4dc8d198808a83de457eb47add995d793417cfb03b33e","schema_version":"1.0","event_id":"sha256:cacb1bf7220e7d483fe4dc8d198808a83de457eb47add995d793417cfb03b33e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/bundle.json","state_url":"https://pith.science/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/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":"2026-07-17T00:45:56Z","links":{"resolver":"https://pith.science/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP","bundle":"https://pith.science/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/bundle.json","state":"https://pith.science/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QP6IQ4DKVM34CYF4L2FXZ2LVTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QP6IQ4DKVM34CYF4L2FXZ2LVTP","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":"f3596aa8574c2793ab43e46ea81e1eb4863792260a67cb9d3750d0184dede2e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T14:24:08Z","title_canon_sha256":"f54ea78615128859bfd35d59465e4d7b541ee118479ee607c4d544dfbf6d07b6"},"schema_version":"1.0","source":{"id":"2208.13628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.13628","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2208.13628v2","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13628","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"QP6IQ4DKVM34","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"QP6IQ4DKVM34CYF4","created_at":"2026-07-05T05:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"QP6IQ4DK","created_at":"2026-07-05T05:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:cacb1bf7220e7d483fe4dc8d198808a83de457eb47add995d793417cfb03b33e","target":"graph","created_at":"2026-07-05T05:03:39Z","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/2208.13628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks. The current trend is to move towards ever larger models and pretraining datasets. This computational headlong rush does not seem reasonable in the long term to move toward sustainable solutions, and de facto excludes academic laboratories with limited resources. In this work, we propose a new framework, dubbed ViCHA, that efficiently exploits the input data to boost the learning by: (a) a new hierarchical cross-modal alignment loss, (b) new self-supervised scheme based on masked image mo","authors_text":"Guillaume Couairon, Matthieu Cord, Mustafa Shukor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T14:24:08Z","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13628","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:ec22e2f8fee73fd2d685a6ecbfde48637ecc657ba036126e9e5965e96de07c28","target":"record","created_at":"2026-07-05T05:03:39Z","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":"f3596aa8574c2793ab43e46ea81e1eb4863792260a67cb9d3750d0184dede2e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T14:24:08Z","title_canon_sha256":"f54ea78615128859bfd35d59465e4d7b541ee118479ee607c4d544dfbf6d07b6"},"schema_version":"1.0","source":{"id":"2208.13628","kind":"arxiv","version":2}},"canonical_sha256":"83fc88706aab37c160bc5e8b7ce9759be698c7655195963da765dbbd3287c200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83fc88706aab37c160bc5e8b7ce9759be698c7655195963da765dbbd3287c200","first_computed_at":"2026-07-05T05:03:39.182962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:39.182962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q323C7p4F8zRO9rfeBlrIjTFz6rUW/ejeX1/MDNvt62O6s0S4OV+NxmnasMKRbi+6azXViac5uM6LJa4X7sOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:39.183299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.13628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec22e2f8fee73fd2d685a6ecbfde48637ecc657ba036126e9e5965e96de07c28","sha256:cacb1bf7220e7d483fe4dc8d198808a83de457eb47add995d793417cfb03b33e"],"state_sha256":"8e98aedd8bb21fae9f6a10eb86f4f503dc409a231818bd723991e06b82cd8687"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zIBQTUgFV6NiYK3NOEXeOEICwW0dkpOrKvY90NgEPwSDgn6aH0Gj7LUX8juN4/T6fzOSiutVt+AgWKIqtwceCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T00:45:56.803910Z","bundle_sha256":"69b3c7b24e26bff3d644a28f0621aab239fff332d487d797ad46b95d436a1093"}}