{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XMXPXC3BF5DKVXFQX2HWQ2DG5T","short_pith_number":"pith:XMXPXC3B","canonical_record":{"source":{"id":"2507.06679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T09:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"b6101de7b01d310ebece6349d58d011da150872b1347be768f16f55181d15797","abstract_canon_sha256":"8f23e91f34171a4903697598087fdafbe9f44f8bd66d57118773708fa8cc1c8e"},"schema_version":"1.0"},"canonical_sha256":"bb2efb8b612f46aadcb0be8f686866ecea561d719d800675fe67ac05a56642cf","source":{"kind":"arxiv","id":"2507.06679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06679","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06679v1","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06679","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"XMXPXC3BF5DK","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"XMXPXC3BF5DKVXFQ","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"XMXPXC3B","created_at":"2026-07-05T11:34:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XMXPXC3BF5DKVXFQX2HWQ2DG5T","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T09:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"b6101de7b01d310ebece6349d58d011da150872b1347be768f16f55181d15797","abstract_canon_sha256":"8f23e91f34171a4903697598087fdafbe9f44f8bd66d57118773708fa8cc1c8e"},"schema_version":"1.0"},"canonical_sha256":"bb2efb8b612f46aadcb0be8f686866ecea561d719d800675fe67ac05a56642cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:21.089106Z","signature_b64":"9GQdNp2E7plXenZ4k1iE6uCUpX9zrkxaAWD6zhtG+Lzxz8OS5noXxlnatLOKS2ssGmzwrw1dhD5nO6H7vOxlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2efb8b612f46aadcb0be8f686866ecea561d719d800675fe67ac05a56642cf","last_reissued_at":"2026-07-05T11:34:21.088613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:21.088613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06679","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":"2026-07-05T11:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hd6pxfM/1YRB8cd/aG1ve2TzA9qTKCm81AmAnpr6C1FaSGi6US4/0W8xNY4og09BtRR1WTB2kAlWUtlFfaNIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:57:13.820388Z"},"content_sha256":"5921461f229a859d491fbd2cb0db6d377d7745eda46c4d34adddd8257280d22a","schema_version":"1.0","event_id":"sha256:5921461f229a859d491fbd2cb0db6d377d7745eda46c4d34adddd8257280d22a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XMXPXC3BF5DKVXFQX2HWQ2DG5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-promptable Object Counting via Quantity Awareness Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cairong Zhao, Li Li, Miaojing Shi, Xiaowen Zhang, Yong Luo, Zijie Yue","submitted_at":"2025-07-09T09:12:33Z","abstract_excerpt":"Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category information in images. This however is insufficient for training the model to accurately distinguish the number of objects in the counting task. To this end, we propose QUANet, which introduces novel quantity-oriented text prompts with a vision-text quantity alignment loss to enhance the model's quantity awareness. Moreover, we propose a dual-stream adaptive counting decoder consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06679","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/2507.06679/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":"2026-07-05T11:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SHAfvcWFXgPYuz8cgn+zgVsH8Cjm/ymgq05RCHttOGp5XCDGhOjeNpRn92TuopTFHs2SN6sna1fuES6KqMEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:57:13.821865Z"},"content_sha256":"ca17aa362a43a32dc33a8732bd6b24b917ba1fc9eff35df0b4bc21e3177315f9","schema_version":"1.0","event_id":"sha256:ca17aa362a43a32dc33a8732bd6b24b917ba1fc9eff35df0b4bc21e3177315f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/bundle.json","state_url":"https://pith.science/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/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":"2026-08-09T06:57:13Z","links":{"resolver":"https://pith.science/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T","bundle":"https://pith.science/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/bundle.json","state":"https://pith.science/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMXPXC3BF5DKVXFQX2HWQ2DG5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XMXPXC3BF5DKVXFQX2HWQ2DG5T","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":"8f23e91f34171a4903697598087fdafbe9f44f8bd66d57118773708fa8cc1c8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T09:12:33Z","title_canon_sha256":"b6101de7b01d310ebece6349d58d011da150872b1347be768f16f55181d15797"},"schema_version":"1.0","source":{"id":"2507.06679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06679","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06679v1","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06679","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"XMXPXC3BF5DK","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"XMXPXC3BF5DKVXFQ","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"XMXPXC3B","created_at":"2026-07-05T11:34:21Z"}],"graph_snapshots":[{"event_id":"sha256:ca17aa362a43a32dc33a8732bd6b24b917ba1fc9eff35df0b4bc21e3177315f9","target":"graph","created_at":"2026-07-05T11:34:21Z","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/2507.06679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category information in images. This however is insufficient for training the model to accurately distinguish the number of objects in the counting task. To this end, we propose QUANet, which introduces novel quantity-oriented text prompts with a vision-text quantity alignment loss to enhance the model's quantity awareness. Moreover, we propose a dual-stream adaptive counting decoder consi","authors_text":"Cairong Zhao, Li Li, Miaojing Shi, Xiaowen Zhang, Yong Luo, Zijie Yue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T09:12:33Z","title":"Text-promptable Object Counting via Quantity Awareness Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06679","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":"sha256:5921461f229a859d491fbd2cb0db6d377d7745eda46c4d34adddd8257280d22a","target":"record","created_at":"2026-07-05T11:34:21Z","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":"8f23e91f34171a4903697598087fdafbe9f44f8bd66d57118773708fa8cc1c8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T09:12:33Z","title_canon_sha256":"b6101de7b01d310ebece6349d58d011da150872b1347be768f16f55181d15797"},"schema_version":"1.0","source":{"id":"2507.06679","kind":"arxiv","version":1}},"canonical_sha256":"bb2efb8b612f46aadcb0be8f686866ecea561d719d800675fe67ac05a56642cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb2efb8b612f46aadcb0be8f686866ecea561d719d800675fe67ac05a56642cf","first_computed_at":"2026-07-05T11:34:21.088613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:21.088613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9GQdNp2E7plXenZ4k1iE6uCUpX9zrkxaAWD6zhtG+Lzxz8OS5noXxlnatLOKS2ssGmzwrw1dhD5nO6H7vOxlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:21.089106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5921461f229a859d491fbd2cb0db6d377d7745eda46c4d34adddd8257280d22a","sha256:ca17aa362a43a32dc33a8732bd6b24b917ba1fc9eff35df0b4bc21e3177315f9"],"state_sha256":"344482eeb131989223915baddca051fca05206eddeca011c4859b3b3d976e560"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vN42PiDQxqE3ShgkjT0Y9fh8LXLS0lXl2uW1RMGcw6FyGatPqP2dBsiFTJpzWDgmpMxSC+/nhh1ScftyK1BSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:57:13.835170Z","bundle_sha256":"f391359708361325eab614d3673f64abac755f041a888d66c50f8e133c8ae114"}}