{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VQRAEP62K7BSYZEPFZQB2COBSN","short_pith_number":"pith:VQRAEP62","canonical_record":{"source":{"id":"2310.13447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T12:26:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"01202f3b50eb7a93150607706879457fbf1a6904d8619037fc5f4c498fd099f9","abstract_canon_sha256":"24b5e7fb25b95b6bc3282946b90e0e308051847dbfa4bc683bc5cfe4886dfb8f"},"schema_version":"1.0"},"canonical_sha256":"ac22023fda57c32c648f2e601d09c1937620a6bd06a2c501a4567c00ff08857b","source":{"kind":"arxiv","id":"2310.13447","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13447","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13447v3","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13447","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"VQRAEP62K7BS","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_16","alias_value":"VQRAEP62K7BSYZEP","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_8","alias_value":"VQRAEP62","created_at":"2026-07-05T08:46:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VQRAEP62K7BSYZEPFZQB2COBSN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T12:26:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"01202f3b50eb7a93150607706879457fbf1a6904d8619037fc5f4c498fd099f9","abstract_canon_sha256":"24b5e7fb25b95b6bc3282946b90e0e308051847dbfa4bc683bc5cfe4886dfb8f"},"schema_version":"1.0"},"canonical_sha256":"ac22023fda57c32c648f2e601d09c1937620a6bd06a2c501a4567c00ff08857b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:18.995903Z","signature_b64":"59knUcJK/JsQ3Xesz42rFdb+FL72kZADK3gkn0lh/JPDk9F50y+IuafxF4XoU7/MSROL7TZZhyWcf4kP16ohBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac22023fda57c32c648f2e601d09c1937620a6bd06a2c501a4567c00ff08857b","last_reissued_at":"2026-07-05T08:46:18.995416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:18.995416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13447","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":"2026-07-05T08:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"koKjR+r9OCvH5ENbziTPX5FTpIgEHy9CgpNM4oZecfU4UtHLRKbelS5GC1clFK3Y4yE5vDDxTNqz9brx5xbMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:41:10.059678Z"},"content_sha256":"61866515ccea8b707c80929e807d0a57145a0f9c19699715fdccb58b30df7dd5","schema_version":"1.0","event_id":"sha256:61866515ccea8b707c80929e807d0a57145a0f9c19699715fdccb58b30df7dd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VQRAEP62K7BSYZEPFZQB2COBSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Superpixel Semantics Representation and Pre-training for Vision-Language Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fang Wang, Jun Yang, Lizhi Bai, Shangce Gao, Siyu Zhang, Yaoru Sun, Yeming Chen","submitted_at":"2023-10-20T12:26:04Z","abstract_excerpt":"The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained semantic interactions in image space should not be ignored, which hinders the extraction of complex contextual semantic relations at the scene boundaries. This paper proposes superpixels as comprehensive and robust visual primitives, which mine coarse-grained semantic interactions by clustering perceptually similar pixels, speeding up the subsequent processi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13447","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/2310.13447/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":"2026-07-05T08:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQGmfWqTEkl92kp9g72pLIUC6Hgv4jm38/Hnqx7pfCCx88wRKqtX1ZYRiRiJuXlKzvuL3GgwgCMLmTcn191eBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:41:10.060068Z"},"content_sha256":"73107cf2d866631a1ca232237a43f00e7c220cc2dd64a17067c43ff099ff486f","schema_version":"1.0","event_id":"sha256:73107cf2d866631a1ca232237a43f00e7c220cc2dd64a17067c43ff099ff486f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQRAEP62K7BSYZEPFZQB2COBSN/bundle.json","state_url":"https://pith.science/pith/VQRAEP62K7BSYZEPFZQB2COBSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQRAEP62K7BSYZEPFZQB2COBSN/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":"2026-07-07T15:41:10Z","links":{"resolver":"https://pith.science/pith/VQRAEP62K7BSYZEPFZQB2COBSN","bundle":"https://pith.science/pith/VQRAEP62K7BSYZEPFZQB2COBSN/bundle.json","state":"https://pith.science/pith/VQRAEP62K7BSYZEPFZQB2COBSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQRAEP62K7BSYZEPFZQB2COBSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQRAEP62K7BSYZEPFZQB2COBSN","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":"24b5e7fb25b95b6bc3282946b90e0e308051847dbfa4bc683bc5cfe4886dfb8f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T12:26:04Z","title_canon_sha256":"01202f3b50eb7a93150607706879457fbf1a6904d8619037fc5f4c498fd099f9"},"schema_version":"1.0","source":{"id":"2310.13447","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13447","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13447v3","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13447","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"VQRAEP62K7BS","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_16","alias_value":"VQRAEP62K7BSYZEP","created_at":"2026-07-05T08:46:18Z"},{"alias_kind":"pith_short_8","alias_value":"VQRAEP62","created_at":"2026-07-05T08:46:18Z"}],"graph_snapshots":[{"event_id":"sha256:73107cf2d866631a1ca232237a43f00e7c220cc2dd64a17067c43ff099ff486f","target":"graph","created_at":"2026-07-05T08:46:18Z","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/2310.13447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained semantic interactions in image space should not be ignored, which hinders the extraction of complex contextual semantic relations at the scene boundaries. This paper proposes superpixels as comprehensive and robust visual primitives, which mine coarse-grained semantic interactions by clustering perceptually similar pixels, speeding up the subsequent processi","authors_text":"Fang Wang, Jun Yang, Lizhi Bai, Shangce Gao, Siyu Zhang, Yaoru Sun, Yeming Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T12:26:04Z","title":"Superpixel Semantics Representation and Pre-training for Vision-Language Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13447","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":"sha256:61866515ccea8b707c80929e807d0a57145a0f9c19699715fdccb58b30df7dd5","target":"record","created_at":"2026-07-05T08:46:18Z","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":"24b5e7fb25b95b6bc3282946b90e0e308051847dbfa4bc683bc5cfe4886dfb8f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T12:26:04Z","title_canon_sha256":"01202f3b50eb7a93150607706879457fbf1a6904d8619037fc5f4c498fd099f9"},"schema_version":"1.0","source":{"id":"2310.13447","kind":"arxiv","version":3}},"canonical_sha256":"ac22023fda57c32c648f2e601d09c1937620a6bd06a2c501a4567c00ff08857b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac22023fda57c32c648f2e601d09c1937620a6bd06a2c501a4567c00ff08857b","first_computed_at":"2026-07-05T08:46:18.995416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:18.995416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"59knUcJK/JsQ3Xesz42rFdb+FL72kZADK3gkn0lh/JPDk9F50y+IuafxF4XoU7/MSROL7TZZhyWcf4kP16ohBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:18.995903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13447","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61866515ccea8b707c80929e807d0a57145a0f9c19699715fdccb58b30df7dd5","sha256:73107cf2d866631a1ca232237a43f00e7c220cc2dd64a17067c43ff099ff486f"],"state_sha256":"922aebb16e26a720d2c457d4f1b49150fb13a12b16b3fdc04fc9ffdc459809d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zA6jgoy0gmZCCV/FiQ0c1c4zbAGmt3hPC4VBCtGBalnc9pr2VURL4D857H2kpFSWLU7yz2ITbIAg9KIUrNqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:41:10.061971Z","bundle_sha256":"36575f554d95d790a1989a052c0d8a84ff2f34665f24336d9d7b9c39a071fb2b"}}