{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YFEIEFXDLZWVQAMP4KD6OGKFMT","short_pith_number":"pith:YFEIEFXD","schema_version":"1.0","canonical_sha256":"c1488216e35e6d58018fe287e7194564f6562fc260ec91fe71a4fc8219039f03","source":{"kind":"arxiv","id":"2601.15224","version":2},"attestation_state":"computed","paper":{"title":"PROGRESSLM: Towards Progress Reasoning in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengxuan Qian, Dingcheng Wang, Han Liu, Haoran Lu, Haosen Sun, Jianshu Zhang, Letian Xue","submitted_at":"2026-01-21T17:56:59Z","abstract_excerpt":"Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing what is visible, it remains unclear whether they can infer how far a task has progressed from partial observations. To this end, we introduce Progress-Bench, a benchmark for systematically evaluating progress reasoning in VLMs. Beyond benchmarking, we further explore a human-inspired two-stage progress reasoning paradigm through both training-free prompting and training-based approach based on curated dataset Progre"},"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":"2601.15224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-21T17:56:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e6eeeec82309ec26ae36618749f9b7abe73bde99bd261015c104c820056b7af4","abstract_canon_sha256":"fab887319caaa5e309fd3ac4d2aebde1393e423fb3ff078983b793a9f9d6e23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:12.486995Z","signature_b64":"3eN/q2MfxJ/0N4LsAe+l+IvOl/T3+Q58+lireoWpCA24SlIHpkdrxCYEbThaxieXe8aD6DdXXHUby7jfyzW1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1488216e35e6d58018fe287e7194564f6562fc260ec91fe71a4fc8219039f03","last_reissued_at":"2026-05-25T02:01:12.486064Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:12.486064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PROGRESSLM: Towards Progress Reasoning in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengxuan Qian, Dingcheng Wang, Han Liu, Haoran Lu, Haosen Sun, Jianshu Zhang, Letian Xue","submitted_at":"2026-01-21T17:56:59Z","abstract_excerpt":"Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing what is visible, it remains unclear whether they can infer how far a task has progressed from partial observations. To this end, we introduce Progress-Bench, a benchmark for systematically evaluating progress reasoning in VLMs. Beyond benchmarking, we further explore a human-inspired two-stage progress reasoning paradigm through both training-free prompting and training-based approach based on curated dataset Progre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15224","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/2601.15224/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":"2601.15224","created_at":"2026-05-25T02:01:12.486177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15224v2","created_at":"2026-05-25T02:01:12.486177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15224","created_at":"2026-05-25T02:01:12.486177+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFEIEFXDLZWV","created_at":"2026-05-25T02:01:12.486177+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFEIEFXDLZWVQAMP","created_at":"2026-05-25T02:01:12.486177+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFEIEFXD","created_at":"2026-05-25T02:01:12.486177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.20682","citing_title":"IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2603.02115","citing_title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT","json":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT.json","graph_json":"https://pith.science/api/pith-number/YFEIEFXDLZWVQAMP4KD6OGKFMT/graph.json","events_json":"https://pith.science/api/pith-number/YFEIEFXDLZWVQAMP4KD6OGKFMT/events.json","paper":"https://pith.science/paper/YFEIEFXD"},"agent_actions":{"view_html":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT","download_json":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT.json","view_paper":"https://pith.science/paper/YFEIEFXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15224&json=true","fetch_graph":"https://pith.science/api/pith-number/YFEIEFXDLZWVQAMP4KD6OGKFMT/graph.json","fetch_events":"https://pith.science/api/pith-number/YFEIEFXDLZWVQAMP4KD6OGKFMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT/action/storage_attestation","attest_author":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT/action/author_attestation","sign_citation":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT/action/citation_signature","submit_replication":"https://pith.science/pith/YFEIEFXDLZWVQAMP4KD6OGKFMT/action/replication_record"}},"created_at":"2026-05-25T02:01:12.486177+00:00","updated_at":"2026-05-25T02:01:12.486177+00:00"}