{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FVAXFNNK56D73AJTSJ5KFB6BIN","short_pith_number":"pith:FVAXFNNK","schema_version":"1.0","canonical_sha256":"2d4172b5aaef87fd8133927aa287c143613900cea077b2a7b24bae67b72ce05f","source":{"kind":"arxiv","id":"2607.20903","version":1},"attestation_state":"computed","paper":{"title":"Sidewalk Moments: Are Richer Representations Always More Human-Aligned? Evidence from City-Walk Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"F\\'abio Duarte, Freya Huying Tan, Liu Liu","submitted_at":"2026-07-23T03:54:34Z","abstract_excerpt":"We examine whether richer visual representations yield more human-aligned measures of urban engagement, using 61 first-person city-walk videos from YouTube segmented into over 50,000 ten-second clips and represented across four modalities: spatiotemporal video features, temporally averaged images (TAIs), audio embeddings, and text-based semantic descriptions. Spearman correlation analysis reveals the expected ordering along the temporal-richness continuum, with video features showing the strongest continuous alignment. However, this ordering breaks down under binary classification of high- ver"},"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":"2607.20903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T03:54:34Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"4bb8f7fcd12cb2a821cb3d494b7a4a02a270b21285a7933642f3828e8ed10463","abstract_canon_sha256":"6e9deebca1c322bfdc2b9869628fa98fb974a7f180f04c9c8e62c1ecbed9b6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:40.807812Z","signature_b64":"XyoH4fAsRTxCtAtIrsOoJCRses/8IwYL4ojuH/ER4xWEC7qUZQvRYHz7ZGO/8nUT8K5Vvi8V2CMQQVzZtWA6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d4172b5aaef87fd8133927aa287c143613900cea077b2a7b24bae67b72ce05f","last_reissued_at":"2026-07-24T00:23:40.806825Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:40.806825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sidewalk Moments: Are Richer Representations Always More Human-Aligned? Evidence from City-Walk Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"F\\'abio Duarte, Freya Huying Tan, Liu Liu","submitted_at":"2026-07-23T03:54:34Z","abstract_excerpt":"We examine whether richer visual representations yield more human-aligned measures of urban engagement, using 61 first-person city-walk videos from YouTube segmented into over 50,000 ten-second clips and represented across four modalities: spatiotemporal video features, temporally averaged images (TAIs), audio embeddings, and text-based semantic descriptions. Spearman correlation analysis reveals the expected ordering along the temporal-richness continuum, with video features showing the strongest continuous alignment. However, this ordering breaks down under binary classification of high- ver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20903","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/2607.20903/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":"2607.20903","created_at":"2026-07-24T00:23:40.807304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20903v1","created_at":"2026-07-24T00:23:40.807304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20903","created_at":"2026-07-24T00:23:40.807304+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVAXFNNK56D7","created_at":"2026-07-24T00:23:40.807304+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVAXFNNK56D73AJT","created_at":"2026-07-24T00:23:40.807304+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVAXFNNK","created_at":"2026-07-24T00:23:40.807304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN","json":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN.json","graph_json":"https://pith.science/api/pith-number/FVAXFNNK56D73AJTSJ5KFB6BIN/graph.json","events_json":"https://pith.science/api/pith-number/FVAXFNNK56D73AJTSJ5KFB6BIN/events.json","paper":"https://pith.science/paper/FVAXFNNK"},"agent_actions":{"view_html":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN","download_json":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN.json","view_paper":"https://pith.science/paper/FVAXFNNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20903&json=true","fetch_graph":"https://pith.science/api/pith-number/FVAXFNNK56D73AJTSJ5KFB6BIN/graph.json","fetch_events":"https://pith.science/api/pith-number/FVAXFNNK56D73AJTSJ5KFB6BIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN/action/storage_attestation","attest_author":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN/action/author_attestation","sign_citation":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN/action/citation_signature","submit_replication":"https://pith.science/pith/FVAXFNNK56D73AJTSJ5KFB6BIN/action/replication_record"}},"created_at":"2026-07-24T00:23:40.807304+00:00","updated_at":"2026-07-24T00:23:40.807304+00:00"}