{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ET3XT3QENA2ZJOREKWHPYAK5AP","short_pith_number":"pith:ET3XT3QE","canonical_record":{"source":{"id":"2412.00740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T09:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"41757225bb9213c074d2d217c9ff8aa2ea1355f43b52dbf5b5dc33db53b0470c","abstract_canon_sha256":"ada7e62ad4d2bd04f213961b663044072278ac6a7fd74db254c51cf49475c248"},"schema_version":"1.0"},"canonical_sha256":"24f779ee04683594ba24558efc015d03cf8e03a640ee93b0d12e34c5df746b13","source":{"kind":"arxiv","id":"2412.00740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00740","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00740v1","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00740","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"ET3XT3QENA2Z","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"ET3XT3QENA2ZJORE","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"ET3XT3QE","created_at":"2026-07-05T09:42:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ET3XT3QENA2ZJOREKWHPYAK5AP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T09:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"41757225bb9213c074d2d217c9ff8aa2ea1355f43b52dbf5b5dc33db53b0470c","abstract_canon_sha256":"ada7e62ad4d2bd04f213961b663044072278ac6a7fd74db254c51cf49475c248"},"schema_version":"1.0"},"canonical_sha256":"24f779ee04683594ba24558efc015d03cf8e03a640ee93b0d12e34c5df746b13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:46.730674Z","signature_b64":"Xw/YmIBtnrTddPo6g2wewO+M2f9dT2/6gsoV0nwZQAu3nKovMzoSygJVqnMGDD325EI1cvn7xOIfjQty/9/QDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f779ee04683594ba24558efc015d03cf8e03a640ee93b0d12e34c5df746b13","last_reissued_at":"2026-07-05T09:42:46.730167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:46.730167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00740","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":"2026-07-05T09:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PuD30iAZn1VQDwki0zYPvSzC5rkrNKjVoHMeSxKLcjIUTJWwikWmAmxyS090zFzDSoB4nl2DYGw/UVVMF7RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:56:15.165200Z"},"content_sha256":"73e1c1be0b94c52776275b36b8fc2e18db1528ce3a1a2ec76577b834d9d34374","schema_version":"1.0","event_id":"sha256:73e1c1be0b94c52776275b36b8fc2e18db1528ce3a1a2ec76577b834d9d34374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ET3XT3QENA2ZJOREKWHPYAK5AP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Liu, Jun Liu, Jun Wan, Wenwen Min, Yujia Wu, Zhihui Lai","submitted_at":"2024-12-01T09:20:32Z","abstract_excerpt":"At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre performance, e.g., they perform well on neutral samples but struggle with faces exhibiting large poses or occlusions. Moreover, they cannot effectively deal with semantic gaps and ambiguities among features at different scales, which may hinder them from learning efficient features. To address the above issues, in this paper, we propose a Dynamic Semantic-Aggregati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00740","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/2412.00740/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":"2026-07-05T09:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Si4Zs8BRttrzKtNTYCN9TfJUjnmdXkhqTZB/9hWTXQD4LFHYcOt7q4qY6tmmEiBWet25RVvCh713qROzgOwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:56:15.165544Z"},"content_sha256":"303ca055b1170a777ed67d6a299d97d005d03cd613cb3ddfa6642dd20cd32f5d","schema_version":"1.0","event_id":"sha256:303ca055b1170a777ed67d6a299d97d005d03cd613cb3ddfa6642dd20cd32f5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/bundle.json","state_url":"https://pith.science/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/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":"2026-08-01T09:56:15Z","links":{"resolver":"https://pith.science/pith/ET3XT3QENA2ZJOREKWHPYAK5AP","bundle":"https://pith.science/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/bundle.json","state":"https://pith.science/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ET3XT3QENA2ZJOREKWHPYAK5AP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ET3XT3QENA2ZJOREKWHPYAK5AP","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":"ada7e62ad4d2bd04f213961b663044072278ac6a7fd74db254c51cf49475c248","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T09:20:32Z","title_canon_sha256":"41757225bb9213c074d2d217c9ff8aa2ea1355f43b52dbf5b5dc33db53b0470c"},"schema_version":"1.0","source":{"id":"2412.00740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00740","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00740v1","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00740","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"ET3XT3QENA2Z","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"ET3XT3QENA2ZJORE","created_at":"2026-07-05T09:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"ET3XT3QE","created_at":"2026-07-05T09:42:46Z"}],"graph_snapshots":[{"event_id":"sha256:303ca055b1170a777ed67d6a299d97d005d03cd613cb3ddfa6642dd20cd32f5d","target":"graph","created_at":"2026-07-05T09:42:46Z","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/2412.00740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre performance, e.g., they perform well on neutral samples but struggle with faces exhibiting large poses or occlusions. Moreover, they cannot effectively deal with semantic gaps and ambiguities among features at different scales, which may hinder them from learning efficient features. To address the above issues, in this paper, we propose a Dynamic Semantic-Aggregati","authors_text":"He Liu, Jun Liu, Jun Wan, Wenwen Min, Yujia Wu, Zhihui Lai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T09:20:32Z","title":"Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00740","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":"sha256:73e1c1be0b94c52776275b36b8fc2e18db1528ce3a1a2ec76577b834d9d34374","target":"record","created_at":"2026-07-05T09:42:46Z","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":"ada7e62ad4d2bd04f213961b663044072278ac6a7fd74db254c51cf49475c248","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T09:20:32Z","title_canon_sha256":"41757225bb9213c074d2d217c9ff8aa2ea1355f43b52dbf5b5dc33db53b0470c"},"schema_version":"1.0","source":{"id":"2412.00740","kind":"arxiv","version":1}},"canonical_sha256":"24f779ee04683594ba24558efc015d03cf8e03a640ee93b0d12e34c5df746b13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24f779ee04683594ba24558efc015d03cf8e03a640ee93b0d12e34c5df746b13","first_computed_at":"2026-07-05T09:42:46.730167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:46.730167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xw/YmIBtnrTddPo6g2wewO+M2f9dT2/6gsoV0nwZQAu3nKovMzoSygJVqnMGDD325EI1cvn7xOIfjQty/9/QDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:46.730674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73e1c1be0b94c52776275b36b8fc2e18db1528ce3a1a2ec76577b834d9d34374","sha256:303ca055b1170a777ed67d6a299d97d005d03cd613cb3ddfa6642dd20cd32f5d"],"state_sha256":"7ae7073ca6382d6f14af6aa87f15b6c39a39ea423f03730b762172fe0b5b989e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nLUATqX+AZlmgIsBROmBkvEx81JqNkMAqGLV+q+XrBdyVDwl9wCJvZMzSAgRokL7jeo/sZ89uGUXtoNeyfcBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:56:15.168987Z","bundle_sha256":"ef379b915e6a8d7caaac63a8bb12a9c84c473f837531292a69f3f4bc0a094e5c"}}