{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DQ7WGH2JCRJK3UZYMURHQE2MRO","short_pith_number":"pith:DQ7WGH2J","canonical_record":{"source":{"id":"2412.19504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T07:44:05Z","cross_cats_sorted":[],"title_canon_sha256":"1037019780e591eabf2b35a830850ba5ff8aeed17200c65c5bf31bf17375967c","abstract_canon_sha256":"455d5cc65a7955df8b14ab813dfde7131252bd24e959277053f8a44bafe2a25a"},"schema_version":"1.0"},"canonical_sha256":"1c3f631f491452add338652278134c8b96e2f77baedf267e4c3fb647ebf7d210","source":{"kind":"arxiv","id":"2412.19504","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19504","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19504v3","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19504","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"DQ7WGH2JCRJK","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"DQ7WGH2JCRJK3UZY","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"DQ7WGH2J","created_at":"2026-07-05T10:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DQ7WGH2JCRJK3UZYMURHQE2MRO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T07:44:05Z","cross_cats_sorted":[],"title_canon_sha256":"1037019780e591eabf2b35a830850ba5ff8aeed17200c65c5bf31bf17375967c","abstract_canon_sha256":"455d5cc65a7955df8b14ab813dfde7131252bd24e959277053f8a44bafe2a25a"},"schema_version":"1.0"},"canonical_sha256":"1c3f631f491452add338652278134c8b96e2f77baedf267e4c3fb647ebf7d210","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:17.491339Z","signature_b64":"5mFHEK+tHadXaX6qvtMh1wv/9amr8wypt5QxwIc2n7diCES3pn1A7W5inCQ/NXA+cvkB1lPUeAKk7z2pxTo7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3f631f491452add338652278134c8b96e2f77baedf267e4c3fb647ebf7d210","last_reissued_at":"2026-07-05T10:52:17.490759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:17.490759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19504","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":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eEu2LQPuxuRDMc4buUKePJbhoYY0qxjYl2jd1JmKhXT7Swh5NNOy40rwxV5lu5jNdSYNulQgy2TvOuuS9TitDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:13:21.594440Z"},"content_sha256":"d60db40cbc5b463b336ad1be898a16cb948cbfc0fb2ff495c3404ba1529cfe68","schema_version":"1.0","event_id":"sha256:d60db40cbc5b463b336ad1be898a16cb948cbfc0fb2ff495c3404ba1529cfe68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DQ7WGH2JCRJK3UZYMURHQE2MRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hear the Scene: Audio-Enhanced Text Spotting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Jing Li","submitted_at":"2024-12-27T07:44:05Z","abstract_excerpt":"Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach that leverages only transcription annotations for training text spotting models, substantially reducing the dependency on elaborate annotation processes. Our methodology employs a query-based paradigm that facilitates the learning of implicit location features through the interaction between text queries and image embeddings. These features are later refine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19504","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/2412.19504/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":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H/Mo8qd1AM1mNQewsnaBb9xMYajbBItK9zAmYzCq182A2j+X2+93gMaWSLFFtCchAyuJF7EpqwDwgQL9N6rNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:13:21.595352Z"},"content_sha256":"d0769ebf11c961b1257587ef920c5ff61f6c67bfc9faeeb525d8bf8545cc8d85","schema_version":"1.0","event_id":"sha256:d0769ebf11c961b1257587ef920c5ff61f6c67bfc9faeeb525d8bf8545cc8d85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/bundle.json","state_url":"https://pith.science/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/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":"2026-08-21T11:13:21Z","links":{"resolver":"https://pith.science/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO","bundle":"https://pith.science/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/bundle.json","state":"https://pith.science/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQ7WGH2JCRJK3UZYMURHQE2MRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DQ7WGH2JCRJK3UZYMURHQE2MRO","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":"455d5cc65a7955df8b14ab813dfde7131252bd24e959277053f8a44bafe2a25a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T07:44:05Z","title_canon_sha256":"1037019780e591eabf2b35a830850ba5ff8aeed17200c65c5bf31bf17375967c"},"schema_version":"1.0","source":{"id":"2412.19504","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19504","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19504v3","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19504","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"DQ7WGH2JCRJK","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"DQ7WGH2JCRJK3UZY","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"DQ7WGH2J","created_at":"2026-07-05T10:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:d0769ebf11c961b1257587ef920c5ff61f6c67bfc9faeeb525d8bf8545cc8d85","target":"graph","created_at":"2026-07-05T10:52:17Z","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/2412.19504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach that leverages only transcription annotations for training text spotting models, substantially reducing the dependency on elaborate annotation processes. Our methodology employs a query-based paradigm that facilitates the learning of implicit location features through the interaction between text queries and image embeddings. These features are later refine","authors_text":"Bo Wang, Jing Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T07:44:05Z","title":"Hear the Scene: Audio-Enhanced Text Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19504","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:d60db40cbc5b463b336ad1be898a16cb948cbfc0fb2ff495c3404ba1529cfe68","target":"record","created_at":"2026-07-05T10:52:17Z","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":"455d5cc65a7955df8b14ab813dfde7131252bd24e959277053f8a44bafe2a25a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T07:44:05Z","title_canon_sha256":"1037019780e591eabf2b35a830850ba5ff8aeed17200c65c5bf31bf17375967c"},"schema_version":"1.0","source":{"id":"2412.19504","kind":"arxiv","version":3}},"canonical_sha256":"1c3f631f491452add338652278134c8b96e2f77baedf267e4c3fb647ebf7d210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c3f631f491452add338652278134c8b96e2f77baedf267e4c3fb647ebf7d210","first_computed_at":"2026-07-05T10:52:17.490759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:17.490759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5mFHEK+tHadXaX6qvtMh1wv/9amr8wypt5QxwIc2n7diCES3pn1A7W5inCQ/NXA+cvkB1lPUeAKk7z2pxTo7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:17.491339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19504","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d60db40cbc5b463b336ad1be898a16cb948cbfc0fb2ff495c3404ba1529cfe68","sha256:d0769ebf11c961b1257587ef920c5ff61f6c67bfc9faeeb525d8bf8545cc8d85"],"state_sha256":"dcc448fbc80e5e45ddaba946d97731c182b96c4c6ceb6ee8a5d367af3310eefa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OPtgmDMcMdVpRCaZElHUAezZc5UMxV8Pl3M6//TocFk+dpdlMMT5b7nH+F4x5ueRcfO/h1vIn9xlKKv4vTRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:13:21.601374Z","bundle_sha256":"ffd88649e39d0dc77900a31cc43a60ab26badc8482fcfc56806ca9317927596c"}}