{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AVBWDD5TPAFTOUH2HDJHGKKAAH","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":"b77e728dfbd7ee23b54d319b360cff60f13a141c77c066590703b6fcc57e7451","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T20:53:30Z","title_canon_sha256":"4da8c183a65e3782d43d1f849baefa0d61796c07fccfc223696253284b2b66ca"},"schema_version":"1.0","source":{"id":"2105.05964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05964","created_at":"2026-07-05T02:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05964v1","created_at":"2026-07-05T02:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05964","created_at":"2026-07-05T02:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"AVBWDD5TPAFT","created_at":"2026-07-05T02:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"AVBWDD5TPAFTOUH2","created_at":"2026-07-05T02:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"AVBWDD5T","created_at":"2026-07-05T02:40:02Z"}],"graph_snapshots":[{"event_id":"sha256:4171bf2bf9223a8aa1bab9634ad427867a4ef33867e816b0ea03e14400f35c59","target":"graph","created_at":"2026-07-05T02:40:02Z","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/2105.05964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse trace segment. We propose two novel tasks: (1) predict a trace given an image and caption (i.e., visual grounding), and (2) predict a caption and a trace given only an image. Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded. We present a novel mo","authors_text":"Amy Bearman, Babak Damavandi, Licheng Yu, Ning Zhang, Tamara Berg, Vikas Singh, Zihang Meng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T20:53:30Z","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05964","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":"sha256:6e1c71475badcbf0cb7705782c1c51051614574578c113b69d1ba855efb8aa34","target":"record","created_at":"2026-07-05T02:40:02Z","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":"b77e728dfbd7ee23b54d319b360cff60f13a141c77c066590703b6fcc57e7451","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T20:53:30Z","title_canon_sha256":"4da8c183a65e3782d43d1f849baefa0d61796c07fccfc223696253284b2b66ca"},"schema_version":"1.0","source":{"id":"2105.05964","kind":"arxiv","version":1}},"canonical_sha256":"0543618fb3780b3750fa38d273294001f567c07e430573e5e2c5b0f52fd9c1ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0543618fb3780b3750fa38d273294001f567c07e430573e5e2c5b0f52fd9c1ba","first_computed_at":"2026-07-05T02:40:02.443971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:02.443971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cC1eE+i6+SKNU1kKO/5b7ZXF//jshvPyNmAPj7EH+lbXWvtd+TUbkV7uzln4byyCWI3jvwG5q31QXJKpUFchAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:02.444306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e1c71475badcbf0cb7705782c1c51051614574578c113b69d1ba855efb8aa34","sha256:4171bf2bf9223a8aa1bab9634ad427867a4ef33867e816b0ea03e14400f35c59"],"state_sha256":"5ab1e14c5e6773cd6b2b8953fc8599a703c1de3df0fb04da62a36da256657e29"}