{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XABYAEUYUW5YGGF6Y246Y4RYRL","short_pith_number":"pith:XABYAEUY","canonical_record":{"source":{"id":"2201.12596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c25eed216791c2cde5613369733e04ebd2cc74b2769503cb8eb6824dc225bf77","abstract_canon_sha256":"c18100aa5fd10cc08f1637bbbd2ec4d939ae687799891ae5289d1e475a80e223"},"schema_version":"1.0"},"canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","source":{"kind":"arxiv","id":"2201.12596","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12596","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12596v3","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12596","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"XABYAEUYUW5Y","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"XABYAEUYUW5YGGF6","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"XABYAEUY","created_at":"2026-07-05T04:57:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XABYAEUYUW5YGGF6Y246Y4RYRL","target":"record","payload":{"canonical_record":{"source":{"id":"2201.12596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c25eed216791c2cde5613369733e04ebd2cc74b2769503cb8eb6824dc225bf77","abstract_canon_sha256":"c18100aa5fd10cc08f1637bbbd2ec4d939ae687799891ae5289d1e475a80e223"},"schema_version":"1.0"},"canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:24.062923Z","signature_b64":"O2CJ/k8ODTUO5mxUMtuI85lME0qLZ3TPwHj890PcMuugGF529ElKiN9D5EX6Q27CC/+nBM4dJAJV87cBSpYhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","last_reissued_at":"2026-07-05T04:57:24.062489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:24.062489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.12596","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNrDrGGy/6xUeQomkkBRMz2g21utlm5hGBAltGv+IoKvdnzjncfUJWK2tpsTTh4CJWEQLjr9Dc0aYPfqPUFUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:02:45.730179Z"},"content_sha256":"e7e55fdce2dfb331b9c6b338968abf73a225c623c138e42f94657ec593972888","schema_version":"1.0","event_id":"sha256:e7e55fdce2dfb331b9c6b338968abf73a225c623c138e42f94657ec593972888"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XABYAEUYUW5YGGF6Y246Y4RYRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Huaixiao Tou, Jingjing Chen, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2022-01-29T14:30:59Z","abstract_excerpt":"Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12596","kind":"arxiv","version":3},"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/2201.12596/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":"2026-07-05T04:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbVJsNtGxpqlR24iete4FxlhGR63tzUTpE/ADhwmgnB0Jii+gjuF+xQ7j0ZO/5wQdVueQ/xBSEs8ZVp/BTIpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:02:45.730755Z"},"content_sha256":"fe4aaa9e38de14c6b39e8e584491fb98206fd7f2daa33414a03232cdddd1aba7","schema_version":"1.0","event_id":"sha256:fe4aaa9e38de14c6b39e8e584491fb98206fd7f2daa33414a03232cdddd1aba7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/bundle.json","state_url":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/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":"2026-08-09T17:02:45Z","links":{"resolver":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL","bundle":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/bundle.json","state":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XABYAEUYUW5YGGF6Y246Y4RYRL","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":"c18100aa5fd10cc08f1637bbbd2ec4d939ae687799891ae5289d1e475a80e223","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","title_canon_sha256":"c25eed216791c2cde5613369733e04ebd2cc74b2769503cb8eb6824dc225bf77"},"schema_version":"1.0","source":{"id":"2201.12596","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12596","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12596v3","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12596","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"XABYAEUYUW5Y","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"XABYAEUYUW5YGGF6","created_at":"2026-07-05T04:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"XABYAEUY","created_at":"2026-07-05T04:57:24Z"}],"graph_snapshots":[{"event_id":"sha256:fe4aaa9e38de14c6b39e8e584491fb98206fd7f2daa33414a03232cdddd1aba7","target":"graph","created_at":"2026-07-05T04:57:24Z","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/2201.12596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of bo","authors_text":"Huaixiao Tou, Jingjing Chen, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12596","kind":"arxiv","version":3},"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:e7e55fdce2dfb331b9c6b338968abf73a225c623c138e42f94657ec593972888","target":"record","created_at":"2026-07-05T04:57:24Z","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":"c18100aa5fd10cc08f1637bbbd2ec4d939ae687799891ae5289d1e475a80e223","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","title_canon_sha256":"c25eed216791c2cde5613369733e04ebd2cc74b2769503cb8eb6824dc225bf77"},"schema_version":"1.0","source":{"id":"2201.12596","kind":"arxiv","version":3}},"canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","first_computed_at":"2026-07-05T04:57:24.062489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:24.062489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O2CJ/k8ODTUO5mxUMtuI85lME0qLZ3TPwHj890PcMuugGF529ElKiN9D5EX6Q27CC/+nBM4dJAJV87cBSpYhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:24.062923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12596","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7e55fdce2dfb331b9c6b338968abf73a225c623c138e42f94657ec593972888","sha256:fe4aaa9e38de14c6b39e8e584491fb98206fd7f2daa33414a03232cdddd1aba7"],"state_sha256":"93b781dff77a4389580e919f6caddfc448782d9fd1d12d96d806bd4cfb74b911"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVlcDkV1iQfkw76EsPNfXDOzhqCIig99mngzw++tettW/GE5njHet9+LwXfYUEDPNmosbET35gv0H6NNk7bjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:02:45.734687Z","bundle_sha256":"43e20200ca62625cf6ef75c3e281d76f4823c1de56c4c0b5d9bbbb92c1a31314"}}