{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TRBOZJ5BJE3QTXPITWDV3P5NYQ","short_pith_number":"pith:TRBOZJ5B","schema_version":"1.0","canonical_sha256":"9c42eca7a1493709dde89d875dbfadc40300a1411a804025079cdbed098780b3","source":{"kind":"arxiv","id":"2311.01091","version":2},"attestation_state":"computed","paper":{"title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Dai, Jizhong Han, Junshi Huang, Si Liu, Tianrui Hui, Xiaolin Wei, Xiaoming Wei, Zihan Ding","submitted_at":"2023-11-02T08:55:28Z","abstract_excerpt":"Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.01091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T08:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"0bf1345241a1ef3e68fc73ef44c2325b3369532d84bb4738609d5bdbb7d44564","abstract_canon_sha256":"745938f28034f0edbfadfd5f68a3aa9d92dd58d35947b5659369cbea095dd369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:05.686475Z","signature_b64":"XaINFdxMLNIPS4J2k5orxvFbashDdfDDfx/8YvQR4zTOqLXBSP236RrqLFsloIVHwQmOkDlO50mupTpPhhRCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c42eca7a1493709dde89d875dbfadc40300a1411a804025079cdbed098780b3","last_reissued_at":"2026-07-05T07:54:05.685949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:05.685949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Dai, Jizhong Han, Junshi Huang, Si Liu, Tianrui Hui, Xiaolin Wei, Xiaoming Wei, Zihan Ding","submitted_at":"2023-11-02T08:55:28Z","abstract_excerpt":"Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01091","kind":"arxiv","version":2},"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/2311.01091/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.01091","created_at":"2026-07-05T07:54:05.686018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01091v2","created_at":"2026-07-05T07:54:05.686018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01091","created_at":"2026-07-05T07:54:05.686018+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRBOZJ5BJE3Q","created_at":"2026-07-05T07:54:05.686018+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRBOZJ5BJE3QTXPI","created_at":"2026-07-05T07:54:05.686018+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRBOZJ5B","created_at":"2026-07-05T07:54:05.686018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20020","citing_title":"GS: Generative Segmentation via Label Diffusion","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ","json":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ.json","graph_json":"https://pith.science/api/pith-number/TRBOZJ5BJE3QTXPITWDV3P5NYQ/graph.json","events_json":"https://pith.science/api/pith-number/TRBOZJ5BJE3QTXPITWDV3P5NYQ/events.json","paper":"https://pith.science/paper/TRBOZJ5B"},"agent_actions":{"view_html":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ","download_json":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ.json","view_paper":"https://pith.science/paper/TRBOZJ5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01091&json=true","fetch_graph":"https://pith.science/api/pith-number/TRBOZJ5BJE3QTXPITWDV3P5NYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TRBOZJ5BJE3QTXPITWDV3P5NYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ/action/storage_attestation","attest_author":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ/action/author_attestation","sign_citation":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ/action/citation_signature","submit_replication":"https://pith.science/pith/TRBOZJ5BJE3QTXPITWDV3P5NYQ/action/replication_record"}},"created_at":"2026-07-05T07:54:05.686018+00:00","updated_at":"2026-07-05T07:54:05.686018+00:00"}