{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ED3ZGWVQN56Z3U4ISRBKABR74J","short_pith_number":"pith:ED3ZGWVQ","schema_version":"1.0","canonical_sha256":"20f7935ab06f7d9dd3889442a0063fe276dbae6747350a30554d4a9655f39f50","source":{"kind":"arxiv","id":"2108.01453","version":1},"attestation_state":"computed","paper":{"title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Hao Zhang, Jindong Chen, Lijuan Liu, Maria Wang, Xiaoxue Zang, Yang Song","submitted_at":"2021-07-06T14:03:04Z","abstract_excerpt":"We present a new human-human dialogue dataset - PhotoChat, the first dataset that casts light on the photo sharing behavior in onlin emessaging. PhotoChat contains 12k dialogues, each of which is paired with a user photo that is shared during the conversation. Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context. In addition, for both task"},"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":"2108.01453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-07-06T14:03:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba326a6bcd9b8888fa10ff436cbb80ad2f6ee76cdbe48ec03caba9bd25e6ff24","abstract_canon_sha256":"a06b8e877496db852a0465658ac422a57a9cfd19816c821e1b2ea78893210c12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:03.133680Z","signature_b64":"skf0KVxlilLYYbnze1O4j2Qy/RotlpYyDuCyHMrgQKQrfDO02VqKisARKnR8tpBrtP8uCpgpZcbSu49qpHX7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20f7935ab06f7d9dd3889442a0063fe276dbae6747350a30554d4a9655f39f50","last_reissued_at":"2026-07-05T03:03:03.133146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:03.133146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Hao Zhang, Jindong Chen, Lijuan Liu, Maria Wang, Xiaoxue Zang, Yang Song","submitted_at":"2021-07-06T14:03:04Z","abstract_excerpt":"We present a new human-human dialogue dataset - PhotoChat, the first dataset that casts light on the photo sharing behavior in onlin emessaging. PhotoChat contains 12k dialogues, each of which is paired with a user photo that is shared during the conversation. Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context. In addition, for both task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01453","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/2108.01453/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":"2108.01453","created_at":"2026-07-05T03:03:03.133206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01453v1","created_at":"2026-07-05T03:03:03.133206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01453","created_at":"2026-07-05T03:03:03.133206+00:00"},{"alias_kind":"pith_short_12","alias_value":"ED3ZGWVQN56Z","created_at":"2026-07-05T03:03:03.133206+00:00"},{"alias_kind":"pith_short_16","alias_value":"ED3ZGWVQN56Z3U4I","created_at":"2026-07-05T03:03:03.133206+00:00"},{"alias_kind":"pith_short_8","alias_value":"ED3ZGWVQ","created_at":"2026-07-05T03:03:03.133206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05887","citing_title":"MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J","json":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J.json","graph_json":"https://pith.science/api/pith-number/ED3ZGWVQN56Z3U4ISRBKABR74J/graph.json","events_json":"https://pith.science/api/pith-number/ED3ZGWVQN56Z3U4ISRBKABR74J/events.json","paper":"https://pith.science/paper/ED3ZGWVQ"},"agent_actions":{"view_html":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J","download_json":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J.json","view_paper":"https://pith.science/paper/ED3ZGWVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01453&json=true","fetch_graph":"https://pith.science/api/pith-number/ED3ZGWVQN56Z3U4ISRBKABR74J/graph.json","fetch_events":"https://pith.science/api/pith-number/ED3ZGWVQN56Z3U4ISRBKABR74J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J/action/storage_attestation","attest_author":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J/action/author_attestation","sign_citation":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J/action/citation_signature","submit_replication":"https://pith.science/pith/ED3ZGWVQN56Z3U4ISRBKABR74J/action/replication_record"}},"created_at":"2026-07-05T03:03:03.133206+00:00","updated_at":"2026-07-05T03:03:03.133206+00:00"}